[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77T2B7A8ENXPEGCWN8ASSFQ":3,"skill-same:01M77T2B7A8ENXPEGCWN8ASSFQ":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":32,"commitSha":33,"skillDirectory":34,"forksCount":35,"repositoryHtmlUrl":36,"repositoryHomepageUrl":37,"ownerHtmlUrl":38,"ownerBlogUrl":6,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M77T2B7A8ENXPEGCWN8ASSFQ","revsec-shield",null,"24\u002F7 security monitoring for your OpenClaw agent. Detects prompt injection attacks, malicious skills, and data exfiltration attempts. Delivers plain-English alerts to your WhatsApp when something suspicious is detected. Use when the user asks about agent security, wants to check for threats, asks what RevSec detected, or when running setup for the first time. Also handles the 5-minute background security poll (cron job revsec:alert-poll).","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fr\u002Frevsec-shield\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: revsec-shield\ndescription: >\n  24\u002F7 security monitoring for your OpenClaw agent. Detects prompt injection\n  attacks, malicious skills, and data exfiltration attempts. Delivers plain-English\n  alerts to your WhatsApp when something suspicious is detected. Use when the user\n  asks about agent security, wants to check for threats, asks what RevSec detected,\n  or when running setup for the first time. Also handles the 5-minute background\n  security poll (cron job revsec:alert-poll).\nhomepage: https:\u002F\u002Frevsec.revt2d.com\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"emoji\": \"🛡️\",\n        \"requires\": { \"env\": [\"REVSEC_API_KEY\"] },\n        \"primaryEnv\": \"REVSEC_API_KEY\",\n      },\n  }\n---\n\n# RevSec Shield\n\nOne-line description: 24\u002F7 security monitoring for your OpenClaw agent —\ndelivered to your WhatsApp in plain English.\n\n## Overview\n\n- **What it does:** Monitors your OpenClaw agent for prompt injection attacks,\n  malicious skills, and unexpected configuration changes. Sends WhatsApp alerts\n  when something suspicious is detected.\n- **When to use it:** Install once. It runs silently in the background. You only\n  hear from it when something needs your attention.\n- **Requirements:** A free RevSec account (revsec.revt2d.com\u002Fsignup), WhatsApp\n  connected to OpenClaw, and a `REVSEC_API_KEY` environment variable.\n\nRevSec Shield is a **monitoring and alerting** tool. It detects threats and\nputs them in front of you immediately. You stay in control of what happens next.\n\n**Three operating modes:**\n\n1. **Setup** — first-time configuration, run once, never needs repeating\n2. **Alert poll** — background cron job, runs every 5 minutes silently\n3. **Manual check** — user asks for a status update\n\n---\n\n## Quick Start\n\n### Install\nAsk your OpenClaw agent:\n```\nUse clawhub to install revsec-shield\n```\n\nOr via CLI:\n```bash\nnpm i -g clawhub\nclawhub install revsec-shield\n```\n\n### Configure\nAdd your API key in OpenClaw's environment settings (not shell exports):\n```\nREVSEC_API_KEY=rsk_personal_\u003Cyour_key>\n```\n\nGet your free key at: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n\n### Activate\nAsk your OpenClaw agent:\n```\nRun the revsec-shield setup\n```\n\nThat's it. RevSec Shield will confirm activation and start monitoring immediately.\n\n---\n\n## Environment Variable Contract\n\n| Variable | Purpose | Required | Where to set |\n|---|---|---|---|\n| `REVSEC_API_KEY` | RevSec API authentication key | Yes | OpenClaw runtime environment |\n\nSet via OpenClaw's environment settings UI or `.env` file — never as a shell export.\n\n---\n\n## Core rules (always follow)\n\n- Never ask the user to do something manually that can be done via curl or shell.\n- RevSec detects first, reports second. Never ask the user \"should I flag this?\" —\n  report what was already detected.\n- Keep alert messages plain and human. No JSON, no confidence scores, no\n  technical jargon unless the user asks for detail.\n- State file is `~\u002F.openclaw\u002Frevsec-state.json`. Read before every action.\n  Write after every action that changes state.\n- If the state file is missing, run Setup before anything else.\n- If `REVSEC_API_KEY` is not set, prompt the user to get one and stop.\n- All curl calls must include `-s` (silent) and `-f` (fail on HTTP errors).\n- On any curl failure: log the error to state, stay silent to the user unless\n  it is a setup step or they explicitly asked for a status check.\n- Never re-run setup if it has already completed. Use the existing\n  `openclaw_agent_id` from state for all subsequent API calls.\n\n---\n\n## State file — `~\u002F.openclaw\u002Frevsec-state.json`\n\nRead and write this file to persist identity and poll state across sessions.\n\n**Schema:**\n```json\n{\n  \"openclaw_agent_id\": \"\u003Cuuid — generated once, never changes>\",\n  \"agent_id\": \"\u003Cuuid — returned by RevSec on registration>\",\n  \"org_id\": \"\u003Cuuid — returned by RevSec on registration>\",\n  \"last_poll_at\": \"\u003CISO 8601 timestamp — advanced after each successful poll>\",\n  \"registered_at\": \"\u003CISO 8601 timestamp>\",\n  \"registered_skills\": [\"skill1\", \"skill2\"],\n  \"skill_version\": \"1.0.0\",\n  \"setup_complete\": true\n}\n```\n\n**Read state:**\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json 2>\u002Fdev\u002Fnull || echo \"{}\"\n```\n\n**Write state** (always write the full object, never partial):\n```bash\ncat > ~\u002F.openclaw\u002Frevsec-state.json \u003C\u003C 'EOF'\n{ \u003Cfull updated state object> }\nEOF\n```\n\n---\n\n## Workflow 1 — Setup (run when setup_complete is missing or false)\n\n**BEFORE ANYTHING ELSE — Check if already set up:**\n\nRead state file:\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json 2>\u002Fdev\u002Fnull || echo \"{}\"\n```\n\nIf `setup_complete` is `true`:\n1. Check if cron job exists: `openclaw cron list`\n2. If `revsec:alert-poll` is missing → create it (Step 5 only)\n3. Tell user: \"RevSec Shield is already active and protecting your agent.\"\n4. **STOP — do not proceed with Steps 1–4. Do not re-register.**\n\nOnly run Steps 1–6 if `setup_complete` is missing or false.\n\n### Step 1 — Check for API key\n\n```bash\necho $REVSEC_API_KEY\n```\n\nIf empty or unset, stop and tell the user:\n\n> To activate RevSec Shield, get your free API key at\n> https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n> Then add it to your OpenClaw environment settings:\n> `REVSEC_API_KEY=rsk_personal_\u003Cyour_key>`\n\nDo not proceed until the key is set.\n\n### Step 2 — Generate stable agent identity\n\nGenerate a UUID. This is the `openclaw_agent_id` — it never changes.\n\n```bash\npython3 -c \"import uuid; print(uuid.uuid4())\"\n```\n\nIf python3 is unavailable:\n```bash\ncat \u002Fproc\u002Fsys\u002Fkernel\u002Frandom\u002Fuuid 2>\u002Fdev\u002Fnull || uuidgen\n```\n\nStore this value. It will be written to state in Step 4.\n\n### Step 3 — Collect agent config from OpenClaw environment\n\nGather what is available from the local environment. Do not ask the user\nquestions that can be inferred.\n\n```bash\n# Hostname\nhostname\n\n# OpenClaw model currently configured (read from config)\ncat ~\u002F.openclaw\u002Fopenclaw.json 2>\u002Fdev\u002Fnull | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nprint(d.get('model','unknown'))\n\" 2>\u002Fdev\u002Fnull || echo \"unknown\"\n\n# Skills currently installed (list skill directories)\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || ls ~\u002Fclawd\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n```\n\nCapture the skills list — this becomes the baseline for change detection.\n\n### Step 4 — Register agent with RevSec\n\nConstruct the registration payload from the collected values and call the API.\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Cuuid from Step 2>\",\n    \"skills\": [\u003Ccomma-separated list of installed skill names as strings>],\n    \"model\": \"\u003Cmodel from Step 3>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [\u003Cany external services visible in openclaw.json>],\n    \"hostname\": \"\u003Chostname from Step 3>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\nOn success the API returns `{ \"agent_id\": \"...\", \"action\": \"registered\" }`.\n\nWrite the full state file including the skills baseline:\n\n```bash\ncat > ~\u002F.openclaw\u002Frevsec-state.json \u003C\u003C 'EOF'\n{\n  \"openclaw_agent_id\": \"\u003Cuuid from Step 2>\",\n  \"agent_id\": \"\u003Cagent_id from API response>\",\n  \"org_id\": \"\u003Corg_id from API response if present, else empty string>\",\n  \"last_poll_at\": \"\u003Ccurrent UTC timestamp in ISO 8601>\",\n  \"registered_at\": \"\u003Ccurrent UTC timestamp in ISO 8601>\",\n  \"registered_skills\": [\u003Csame skills list sent to API>],\n  \"skill_version\": \"1.0.0\",\n  \"setup_complete\": true\n}\nEOF\n```\n\n### Step 5 — Schedule the background alert poll\n\nCheck if the cron job already exists:\n\n```bash\nopenclaw cron list\n```\n\nLook for a job named `revsec:alert-poll`. If it exists, skip creation.\n\nIf it does not exist, create it:\n\n```bash\nopenclaw cron add \\\n  --name \"revsec:alert-poll\" \\\n  --model \"google\u002Fgemini-2.0-flash\" \\\n  --schedule \"*\u002F5 * * * *\" \\\n  --prompt \"Run the revsec-shield skill in alert poll mode. Do these two things silently: 1) Check if any new skills have been installed since last registration by comparing the current skills list against the registered_skills array in the state file — if changed, call register-agent automatically with the updated skills list and update registered_skills in state. 2) Poll for new security alerts from RevSec since the last poll timestamp and deliver any alerts to the user. Be completely silent if there are no changes and no alerts.\"\n```\n\n### Step 6 — Confirm setup to the user\n\nTell the user exactly this (keep it short, match the tone):\n\n> ✅ RevSec Shield is active. Your agent is registered and protected.\n>\n> I'll check for threats every 5 minutes and alert you here if anything\n> is detected. You won't hear from me unless something happens.\n>\n> Your dashboard: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n>\n> 📱 **If you use WhatsApp:** Send me a message from WhatsApp now to\n> activate alert delivery. Without this first message, I cannot reach\n> you on WhatsApp when threats are detected. Just say \"Hi\" from the\n> number you connected during setup.\n\n---\n\n## Workflow 2 — Alert poll (triggered by cron job revsec:alert-poll)\n\nThis workflow runs every 5 minutes automatically. It must be fast and silent\nwhen there are no changes and no alerts. Never output anything to the user\nunless there is something they need to know.\n\n### Step 1 — Read state\n\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json\n```\n\nIf state is missing or `setup_complete` is not true, output nothing and stop.\nDo not trigger setup from a cron context.\n\n### Step 1b — Check for config changes (automatic, silent)\n\nGet the current installed skills:\n\n```bash\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || ls ~\u002Fclawd\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n```\n\n**If `registered_skills` is missing from state file:**\nTreat it as an empty list. All current skills are \"new\". Re-register once to\nset the baseline, then write `registered_skills` to state. Stay silent —\nthis is a one-time migration for users upgrading from an older version.\n\n**If the skills list has changed (new skill added or skill removed):**\n\n1. Re-register the agent using the existing `openclaw_agent_id` from state:\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Copenclaw_agent_id from state — never changes>\",\n    \"skills\": [\u003Ccurrent skills list>],\n    \"model\": \"\u003Cmodel from openclaw.json or unknown>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [],\n    \"hostname\": \"\u003Chostname>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\n2. Update `registered_skills` in the state file with the new skills list.\n   Keep all other state values unchanged.\n\n3. Stay completely silent — this is automatic background maintenance.\n   The RevSec policy engine will evaluate the updated config and create\n   violations if any new skills are suspicious. Those violations will be\n   picked up in Step 2 on this same poll cycle.\n\n**If the skills list has not changed:** skip to Step 2.\n\n### Step 2 — Poll for new alerts\n\n```bash\ncurl -sf \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Falerts?since=\u003Clast_poll_at from state>\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\"\n```\n\nIf curl fails (network error, timeout, 5xx): update nothing, stay silent, stop.\nDo not advance `last_poll_at` on failure — the same window will be retried\non the next poll.\n\nIf the response is an empty array `[]`: stay completely silent. Advance\n`last_poll_at` to now and write state. Stop.\n\n### Step 3 — Deliver alerts (only if response is non-empty)\n\nFor each alert in the response, use the `message` field from the API response\ndirectly — it is already formatted for human delivery. Do not add your own\nheaders or reformat it. Do not prepend \"RevSec blocked a threat\" — the\nmessage field already contains the full alert text.\n\nIf there are multiple alerts, deliver them as a single message grouped by\nseverity — critical first, then high, then medium. Use a separator line\nbetween groups only if there are multiple severity levels.\n\nExample output format:\n```\n\u003Cmessage field from API — critical alerts first>\n\n──────────────────────────\n\n\u003Cmessage field from API — medium\u002Flow alerts>\n```\n\n### Step 4 — Advance poll timestamp\n\nAfter successful delivery (or confirmed empty response), update `last_poll_at`\nto the current UTC time and write the full state file.\n\n```bash\npython3 -c \"from datetime import datetime,timezone; print(datetime.now(timezone.utc).isoformat())\"\n```\n\n---\n\n## Workflow 3 — Manual security check (user asks \"how am I protected?\" or \"what did RevSec detect?\")\n\n### Step 1 — Read state\n\nCheck `~\u002F.openclaw\u002Frevsec-state.json`. If setup is not complete, run\nWorkflow 1 first.\n\n### Step 1b — Check cron health (self-healing)\n\n```bash\nopenclaw cron list\n```\n\nIf `revsec:alert-poll` is missing from the list — recreate it silently\nusing Step 5 from Workflow 1, then tell the user:\n\n> Background monitoring was inactive — I've restarted it. Your protection\n> is now fully active again.\n\n### Step 2 — Fetch dashboard summary\n\n```bash\ncurl -sf \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fsummary\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\"\n```\n\n### Step 3 — Report to user\n\nUse the summary data to report in plain language. Follow this format exactly:\n\n```\n🛡️ RevSec Shield — last 7 days\n\nThreats detected: \u003Cthreats_blocked_7d>\nFlagged for review: \u003Cthreats_flagged_7d>\nAgent: \u003Cagent.name> (\u003Cagent.agent_framework>)\nStatus: \u003Cagent.status>\nPolicies active: \u003Cactive_policies>\n\nFull details: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n```\n\nIf `threats_blocked_7d` and `threats_flagged_7d` are both 0:\n\n```\n🛡️ RevSec Shield — no threats detected in the last 7 days.\nYour agent is clean. Protection is active.\n```\n\n---\n\n## Workflow 4 — Config update (automatic via cron, or triggered manually)\n\nThis workflow is called automatically by the cron job when a config change\nis detected. It can also be triggered manually if the user explicitly asks\nto update their RevSec registration.\n\nThe user never needs to run this manually — it happens automatically.\n\n### Step 1 — Read current state\n\nGet `openclaw_agent_id` from `~\u002F.openclaw\u002Frevsec-state.json`.\n\n### Step 2 — Collect current config\n\n```bash\n# Current skills\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n\n# Current model\ncat ~\u002F.openclaw\u002Fopenclaw.json 2>\u002Fdev\u002Fnull | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nprint(d.get('model','unknown'))\n\" 2>\u002Fdev\u002Fnull || echo \"unknown\"\n\n# Hostname\nhostname\n```\n\n### Step 3 — Re-register with updated config\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Copenclaw_agent_id from state — never changes>\",\n    \"skills\": [\u003Ccurrent skills list>],\n    \"model\": \"\u003Ccurrent model>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [],\n    \"hostname\": \"\u003Chostname>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\n### Step 4 — Update state file\n\nUpdate `registered_skills` in the state file with the new skills list.\nKeep all other state values unchanged — especially `openclaw_agent_id`.\n\nIf triggered manually by the user, confirm:\n\n> ✅ RevSec updated — your agent profile is now in sync.\n\nIf triggered automatically by cron, stay silent.\n\n---\n\n## Security & Guardrails\n\n- **No message content sent:** RevSec only receives agent metadata — skill names,\n  hostname, model. Your conversations and message content are never sent to RevSec.\n- **Credentials:** API key stored in OpenClaw runtime environment only.\n  Never logged or transmitted beyond the RevSec API.\n- **Network access:** Only connects to `revsec.revt2d.com`. No other outbound\n  connections are made by this skill.\n- **Local storage:** State stored only in `~\u002F.openclaw\u002Frevsec-state.json`.\n  No other local files are created or modified.\n- **Fail-closed on API errors:** If RevSec API is unreachable, skill stays\n  silent and retries on next poll. Agent behaviour is never modified.\n- **No pipe-to-interpreter:** No `curl | bash`, `curl | python`, or similar\n  patterns are used anywhere in this skill.\n- **No credential harvesting:** This skill does not read environment variables\n  beyond `REVSEC_API_KEY`, does not access credential files, and does not\n  transmit system information beyond hostname and skill names.\n- **Read-only agent monitoring:** This skill never modifies OpenClaw settings,\n  agent configuration, or installed skills.\n\n---\n\n## Error handling\n\n| Situation | Action |\n|---|---|\n| `REVSEC_API_KEY` not set | Stop, prompt user to get key at signup URL |\n| State file missing during cron poll | Stay silent, stop |\n| curl timeout during cron poll | Stay silent, do not advance timestamp |\n| HTTP 429 from API | Stay silent, do not advance timestamp. On manual check, tell user: \"You've hit the daily scan limit. Upgrade at https:\u002F\u002Frevsec.revt2d.com\u002Fupgrade\" |\n| HTTP 401 from API | Tell user their API key may have expired. Direct to dashboard to rotate: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal |\n| HTTP 5xx from API | Stay silent during cron. On manual check, say: \"RevSec is temporarily unavailable — protection resumes automatically.\" |\n| Registration fails | Tell user registration failed, show the curl error, ask them to try again |\n| New skill detected but re-registration fails | Stay silent, retry on next cron run |\n| Cron job missing | Recreate silently during next manual check (Workflow 3 Step 1b) |\n| WhatsApp alerts not arriving | Remind user to send first message from WhatsApp to establish session |\n\n---\n\n## Troubleshooting\n\n| Error | Fix |\n|---|---|\n| `No API key found` | Set `REVSEC_API_KEY` in OpenClaw environment settings |\n| `401 Unauthorized` | Check key starts with `rsk_personal_` and is complete (77 chars) |\n| `429 Agent limit` | Free tier supports 1 agent — upgrade at revsec.revt2d.com\u002Fupgrade |\n| Cron job errors | Ask agent: \"Run the revsec-shield setup\" to recreate cron job |\n| No WhatsApp alerts | Send a message to OpenClaw from WhatsApp first to establish session |\n| `registered_skills` missing | Cron will auto-fix on next run — no action needed |\n| Setup re-runs every time | Check state file has `\"setup_complete\": true` |\n\n---\n\n## What RevSec Shield does NOT do\n\n- It does not change any OpenClaw settings or configuration\n- It does not access any data beyond what the agent config exposes\n- It does not store any data locally beyond `~\u002F.openclaw\u002Frevsec-state.json`\n- It does not send prompts or conversation content to RevSec — only metadata\n- It does not block or modify LLM calls directly — it monitors agent\n  configuration and behaviour via the RevSec API\n- It does not initiate WhatsApp sessions — user must send first message\n\n---\n\n## Cron job reference\n\n| Job name | Schedule | Purpose |\n|---|---|---|\n| `revsec:alert-poll` | `*\u002F5 * * * *` | Auto-detect config changes + poll for threats |\n\nUse `openclaw cron list` to verify the job is registered.\nUse `openclaw cron runs revsec:alert-poll` to see recent run history.\n\n---\n\n## Release notes\n\n**v1.0.0** — Initial public release\n- Agent registration and monitoring\n- 5-minute background polling\n- WhatsApp alert delivery\n- Automatic config change detection\n- New integration alerts\n- Personal security dashboard at revsec.revt2d.com\u002Fpersonal\n\n---\n\n## Links\n\n- Dashboard: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n- Free signup: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n- Team plan: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\u002Fteam\n- Support: hello@revupai.com\n\n---\n\n## Publisher\n\n- **Publisher:** @RevUp-AI\n- **Homepage:** https:\u002F\u002Frevsec.revt2d.com\n- **Support:** hello@revupai.com\n- **GitHub:** https:\u002F\u002Fgithub.com\u002FRevUp-AI\u002Frevsec-shield","# RevSec Shield\n\nOne-line description: 24\u002F7 security monitoring for your OpenClaw agent —\ndelivered to your WhatsApp in plain English.\n\n## Overview\n\n- **What it does:** Monitors your OpenClaw agent for prompt injection attacks,\n  malicious skills, and unexpected configuration changes. Sends WhatsApp alerts\n  when something suspicious is detected.\n- **When to use it:** Install once. It runs silently in the background. You only\n  hear from it when something needs your attention.\n- **Requirements:** A free RevSec account (revsec.revt2d.com\u002Fsignup), WhatsApp\n  connected to OpenClaw, and a `REVSEC_API_KEY` environment variable.\n\nRevSec Shield is a **monitoring and alerting** tool. It detects threats and\nputs them in front of you immediately. You stay in control of what happens next.\n\n**Three operating modes:**\n\n1. **Setup** — first-time configuration, run once, never needs repeating\n2. **Alert poll** — background cron job, runs every 5 minutes silently\n3. **Manual check** — user asks for a status update\n\n---\n\n## Quick Start\n\n### Install\nAsk your OpenClaw agent:\n```\nUse clawhub to install revsec-shield\n```\n\nOr via CLI:\n```bash\nnpm i -g clawhub\nclawhub install revsec-shield\n```\n\n### Configure\nAdd your API key in OpenClaw's environment settings (not shell exports):\n```\nREVSEC_API_KEY=rsk_personal_\u003Cyour_key>\n```\n\nGet your free key at: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n\n### Activate\nAsk your OpenClaw agent:\n```\nRun the revsec-shield setup\n```\n\nThat's it. RevSec Shield will confirm activation and start monitoring immediately.\n\n---\n\n## Environment Variable Contract\n\n| Variable | Purpose | Required | Where to set |\n|---|---|---|---|\n| `REVSEC_API_KEY` | RevSec API authentication key | Yes | OpenClaw runtime environment |\n\nSet via OpenClaw's environment settings UI or `.env` file — never as a shell export.\n\n---\n\n## Core rules (always follow)\n\n- Never ask the user to do something manually that can be done via curl or shell.\n- RevSec detects first, reports second. Never ask the user \"should I flag this?\" —\n  report what was already detected.\n- Keep alert messages plain and human. No JSON, no confidence scores, no\n  technical jargon unless the user asks for detail.\n- State file is `~\u002F.openclaw\u002Frevsec-state.json`. Read before every action.\n  Write after every action that changes state.\n- If the state file is missing, run Setup before anything else.\n- If `REVSEC_API_KEY` is not set, prompt the user to get one and stop.\n- All curl calls must include `-s` (silent) and `-f` (fail on HTTP errors).\n- On any curl failure: log the error to state, stay silent to the user unless\n  it is a setup step or they explicitly asked for a status check.\n- Never re-run setup if it has already completed. Use the existing\n  `openclaw_agent_id` from state for all subsequent API calls.\n\n---\n\n## State file — `~\u002F.openclaw\u002Frevsec-state.json`\n\nRead and write this file to persist identity and poll state across sessions.\n\n**Schema:**\n```json\n{\n  \"openclaw_agent_id\": \"\u003Cuuid — generated once, never changes>\",\n  \"agent_id\": \"\u003Cuuid — returned by RevSec on registration>\",\n  \"org_id\": \"\u003Cuuid — returned by RevSec on registration>\",\n  \"last_poll_at\": \"\u003CISO 8601 timestamp — advanced after each successful poll>\",\n  \"registered_at\": \"\u003CISO 8601 timestamp>\",\n  \"registered_skills\": [\"skill1\", \"skill2\"],\n  \"skill_version\": \"1.0.0\",\n  \"setup_complete\": true\n}\n```\n\n**Read state:**\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json 2>\u002Fdev\u002Fnull || echo \"{}\"\n```\n\n**Write state** (always write the full object, never partial):\n```bash\ncat > ~\u002F.openclaw\u002Frevsec-state.json \u003C\u003C 'EOF'\n{ \u003Cfull updated state object> }\nEOF\n```\n\n---\n\n## Workflow 1 — Setup (run when setup_complete is missing or false)\n\n**BEFORE ANYTHING ELSE — Check if already set up:**\n\nRead state file:\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json 2>\u002Fdev\u002Fnull || echo \"{}\"\n```\n\nIf `setup_complete` is `true`:\n1. Check if cron job exists: `openclaw cron list`\n2. If `revsec:alert-poll` is missing → create it (Step 5 only)\n3. Tell user: \"RevSec Shield is already active and protecting your agent.\"\n4. **STOP — do not proceed with Steps 1–4. Do not re-register.**\n\nOnly run Steps 1–6 if `setup_complete` is missing or false.\n\n### Step 1 — Check for API key\n\n```bash\necho $REVSEC_API_KEY\n```\n\nIf empty or unset, stop and tell the user:\n\n> To activate RevSec Shield, get your free API key at\n> https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n> Then add it to your OpenClaw environment settings:\n> `REVSEC_API_KEY=rsk_personal_\u003Cyour_key>`\n\nDo not proceed until the key is set.\n\n### Step 2 — Generate stable agent identity\n\nGenerate a UUID. This is the `openclaw_agent_id` — it never changes.\n\n```bash\npython3 -c \"import uuid; print(uuid.uuid4())\"\n```\n\nIf python3 is unavailable:\n```bash\ncat \u002Fproc\u002Fsys\u002Fkernel\u002Frandom\u002Fuuid 2>\u002Fdev\u002Fnull || uuidgen\n```\n\nStore this value. It will be written to state in Step 4.\n\n### Step 3 — Collect agent config from OpenClaw environment\n\nGather what is available from the local environment. Do not ask the user\nquestions that can be inferred.\n\n```bash\n# Hostname\nhostname\n\n# OpenClaw model currently configured (read from config)\ncat ~\u002F.openclaw\u002Fopenclaw.json 2>\u002Fdev\u002Fnull | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nprint(d.get('model','unknown'))\n\" 2>\u002Fdev\u002Fnull || echo \"unknown\"\n\n# Skills currently installed (list skill directories)\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || ls ~\u002Fclawd\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n```\n\nCapture the skills list — this becomes the baseline for change detection.\n\n### Step 4 — Register agent with RevSec\n\nConstruct the registration payload from the collected values and call the API.\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Cuuid from Step 2>\",\n    \"skills\": [\u003Ccomma-separated list of installed skill names as strings>],\n    \"model\": \"\u003Cmodel from Step 3>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [\u003Cany external services visible in openclaw.json>],\n    \"hostname\": \"\u003Chostname from Step 3>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\nOn success the API returns `{ \"agent_id\": \"...\", \"action\": \"registered\" }`.\n\nWrite the full state file including the skills baseline:\n\n```bash\ncat > ~\u002F.openclaw\u002Frevsec-state.json \u003C\u003C 'EOF'\n{\n  \"openclaw_agent_id\": \"\u003Cuuid from Step 2>\",\n  \"agent_id\": \"\u003Cagent_id from API response>\",\n  \"org_id\": \"\u003Corg_id from API response if present, else empty string>\",\n  \"last_poll_at\": \"\u003Ccurrent UTC timestamp in ISO 8601>\",\n  \"registered_at\": \"\u003Ccurrent UTC timestamp in ISO 8601>\",\n  \"registered_skills\": [\u003Csame skills list sent to API>],\n  \"skill_version\": \"1.0.0\",\n  \"setup_complete\": true\n}\nEOF\n```\n\n### Step 5 — Schedule the background alert poll\n\nCheck if the cron job already exists:\n\n```bash\nopenclaw cron list\n```\n\nLook for a job named `revsec:alert-poll`. If it exists, skip creation.\n\nIf it does not exist, create it:\n\n```bash\nopenclaw cron add \\\n  --name \"revsec:alert-poll\" \\\n  --model \"google\u002Fgemini-2.0-flash\" \\\n  --schedule \"*\u002F5 * * * *\" \\\n  --prompt \"Run the revsec-shield skill in alert poll mode. Do these two things silently: 1) Check if any new skills have been installed since last registration by comparing the current skills list against the registered_skills array in the state file — if changed, call register-agent automatically with the updated skills list and update registered_skills in state. 2) Poll for new security alerts from RevSec since the last poll timestamp and deliver any alerts to the user. Be completely silent if there are no changes and no alerts.\"\n```\n\n### Step 6 — Confirm setup to the user\n\nTell the user exactly this (keep it short, match the tone):\n\n> ✅ RevSec Shield is active. Your agent is registered and protected.\n>\n> I'll check for threats every 5 minutes and alert you here if anything\n> is detected. You won't hear from me unless something happens.\n>\n> Your dashboard: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n>\n> 📱 **If you use WhatsApp:** Send me a message from WhatsApp now to\n> activate alert delivery. Without this first message, I cannot reach\n> you on WhatsApp when threats are detected. Just say \"Hi\" from the\n> number you connected during setup.\n\n---\n\n## Workflow 2 — Alert poll (triggered by cron job revsec:alert-poll)\n\nThis workflow runs every 5 minutes automatically. It must be fast and silent\nwhen there are no changes and no alerts. Never output anything to the user\nunless there is something they need to know.\n\n### Step 1 — Read state\n\n```bash\ncat ~\u002F.openclaw\u002Frevsec-state.json\n```\n\nIf state is missing or `setup_complete` is not true, output nothing and stop.\nDo not trigger setup from a cron context.\n\n### Step 1b — Check for config changes (automatic, silent)\n\nGet the current installed skills:\n\n```bash\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || ls ~\u002Fclawd\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n```\n\n**If `registered_skills` is missing from state file:**\nTreat it as an empty list. All current skills are \"new\". Re-register once to\nset the baseline, then write `registered_skills` to state. Stay silent —\nthis is a one-time migration for users upgrading from an older version.\n\n**If the skills list has changed (new skill added or skill removed):**\n\n1. Re-register the agent using the existing `openclaw_agent_id` from state:\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Copenclaw_agent_id from state — never changes>\",\n    \"skills\": [\u003Ccurrent skills list>],\n    \"model\": \"\u003Cmodel from openclaw.json or unknown>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [],\n    \"hostname\": \"\u003Chostname>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\n2. Update `registered_skills` in the state file with the new skills list.\n   Keep all other state values unchanged.\n\n3. Stay completely silent — this is automatic background maintenance.\n   The RevSec policy engine will evaluate the updated config and create\n   violations if any new skills are suspicious. Those violations will be\n   picked up in Step 2 on this same poll cycle.\n\n**If the skills list has not changed:** skip to Step 2.\n\n### Step 2 — Poll for new alerts\n\n```bash\ncurl -sf \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Falerts?since=\u003Clast_poll_at from state>\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\"\n```\n\nIf curl fails (network error, timeout, 5xx): update nothing, stay silent, stop.\nDo not advance `last_poll_at` on failure — the same window will be retried\non the next poll.\n\nIf the response is an empty array `[]`: stay completely silent. Advance\n`last_poll_at` to now and write state. Stop.\n\n### Step 3 — Deliver alerts (only if response is non-empty)\n\nFor each alert in the response, use the `message` field from the API response\ndirectly — it is already formatted for human delivery. Do not add your own\nheaders or reformat it. Do not prepend \"RevSec blocked a threat\" — the\nmessage field already contains the full alert text.\n\nIf there are multiple alerts, deliver them as a single message grouped by\nseverity — critical first, then high, then medium. Use a separator line\nbetween groups only if there are multiple severity levels.\n\nExample output format:\n```\n\u003Cmessage field from API — critical alerts first>\n\n──────────────────────────\n\n\u003Cmessage field from API — medium\u002Flow alerts>\n```\n\n### Step 4 — Advance poll timestamp\n\nAfter successful delivery (or confirmed empty response), update `last_poll_at`\nto the current UTC time and write the full state file.\n\n```bash\npython3 -c \"from datetime import datetime,timezone; print(datetime.now(timezone.utc).isoformat())\"\n```\n\n---\n\n## Workflow 3 — Manual security check (user asks \"how am I protected?\" or \"what did RevSec detect?\")\n\n### Step 1 — Read state\n\nCheck `~\u002F.openclaw\u002Frevsec-state.json`. If setup is not complete, run\nWorkflow 1 first.\n\n### Step 1b — Check cron health (self-healing)\n\n```bash\nopenclaw cron list\n```\n\nIf `revsec:alert-poll` is missing from the list — recreate it silently\nusing Step 5 from Workflow 1, then tell the user:\n\n> Background monitoring was inactive — I've restarted it. Your protection\n> is now fully active again.\n\n### Step 2 — Fetch dashboard summary\n\n```bash\ncurl -sf \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fsummary\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\"\n```\n\n### Step 3 — Report to user\n\nUse the summary data to report in plain language. Follow this format exactly:\n\n```\n🛡️ RevSec Shield — last 7 days\n\nThreats detected: \u003Cthreats_blocked_7d>\nFlagged for review: \u003Cthreats_flagged_7d>\nAgent: \u003Cagent.name> (\u003Cagent.agent_framework>)\nStatus: \u003Cagent.status>\nPolicies active: \u003Cactive_policies>\n\nFull details: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n```\n\nIf `threats_blocked_7d` and `threats_flagged_7d` are both 0:\n\n```\n🛡️ RevSec Shield — no threats detected in the last 7 days.\nYour agent is clean. Protection is active.\n```\n\n---\n\n## Workflow 4 — Config update (automatic via cron, or triggered manually)\n\nThis workflow is called automatically by the cron job when a config change\nis detected. It can also be triggered manually if the user explicitly asks\nto update their RevSec registration.\n\nThe user never needs to run this manually — it happens automatically.\n\n### Step 1 — Read current state\n\nGet `openclaw_agent_id` from `~\u002F.openclaw\u002Frevsec-state.json`.\n\n### Step 2 — Collect current config\n\n```bash\n# Current skills\nls ~\u002F.openclaw\u002Fskills\u002F 2>\u002Fdev\u002Fnull || echo \"\"\n\n# Current model\ncat ~\u002F.openclaw\u002Fopenclaw.json 2>\u002Fdev\u002Fnull | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nprint(d.get('model','unknown'))\n\" 2>\u002Fdev\u002Fnull || echo \"unknown\"\n\n# Hostname\nhostname\n```\n\n### Step 3 — Re-register with updated config\n\n```bash\ncurl -sf -X POST \\\n  \"https:\u002F\u002Frevsec.revt2d.com\u002Ffcc\u002Fapi\u002Fv1\u002Fpersonal\u002Fregister-agent\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -H \"Authorization: Bearer $REVSEC_API_KEY\" \\\n  -d '{\n    \"openclaw_agent_id\": \"\u003Copenclaw_agent_id from state — never changes>\",\n    \"skills\": [\u003Ccurrent skills list>],\n    \"model\": \"\u003Ccurrent model>\",\n    \"channels\": [\"openclaw\"],\n    \"integrations\": [],\n    \"hostname\": \"\u003Chostname>\",\n    \"skill_version\": \"1.0.0\"\n  }'\n```\n\n### Step 4 — Update state file\n\nUpdate `registered_skills` in the state file with the new skills list.\nKeep all other state values unchanged — especially `openclaw_agent_id`.\n\nIf triggered manually by the user, confirm:\n\n> ✅ RevSec updated — your agent profile is now in sync.\n\nIf triggered automatically by cron, stay silent.\n\n---\n\n## Security & Guardrails\n\n- **No message content sent:** RevSec only receives agent metadata — skill names,\n  hostname, model. Your conversations and message content are never sent to RevSec.\n- **Credentials:** API key stored in OpenClaw runtime environment only.\n  Never logged or transmitted beyond the RevSec API.\n- **Network access:** Only connects to `revsec.revt2d.com`. No other outbound\n  connections are made by this skill.\n- **Local storage:** State stored only in `~\u002F.openclaw\u002Frevsec-state.json`.\n  No other local files are created or modified.\n- **Fail-closed on API errors:** If RevSec API is unreachable, skill stays\n  silent and retries on next poll. Agent behaviour is never modified.\n- **No pipe-to-interpreter:** No `curl | bash`, `curl | python`, or similar\n  patterns are used anywhere in this skill.\n- **No credential harvesting:** This skill does not read environment variables\n  beyond `REVSEC_API_KEY`, does not access credential files, and does not\n  transmit system information beyond hostname and skill names.\n- **Read-only agent monitoring:** This skill never modifies OpenClaw settings,\n  agent configuration, or installed skills.\n\n---\n\n## Error handling\n\n| Situation | Action |\n|---|---|\n| `REVSEC_API_KEY` not set | Stop, prompt user to get key at signup URL |\n| State file missing during cron poll | Stay silent, stop |\n| curl timeout during cron poll | Stay silent, do not advance timestamp |\n| HTTP 429 from API | Stay silent, do not advance timestamp. On manual check, tell user: \"You've hit the daily scan limit. Upgrade at https:\u002F\u002Frevsec.revt2d.com\u002Fupgrade\" |\n| HTTP 401 from API | Tell user their API key may have expired. Direct to dashboard to rotate: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal |\n| HTTP 5xx from API | Stay silent during cron. On manual check, say: \"RevSec is temporarily unavailable — protection resumes automatically.\" |\n| Registration fails | Tell user registration failed, show the curl error, ask them to try again |\n| New skill detected but re-registration fails | Stay silent, retry on next cron run |\n| Cron job missing | Recreate silently during next manual check (Workflow 3 Step 1b) |\n| WhatsApp alerts not arriving | Remind user to send first message from WhatsApp to establish session |\n\n---\n\n## Troubleshooting\n\n| Error | Fix |\n|---|---|\n| `No API key found` | Set `REVSEC_API_KEY` in OpenClaw environment settings |\n| `401 Unauthorized` | Check key starts with `rsk_personal_` and is complete (77 chars) |\n| `429 Agent limit` | Free tier supports 1 agent — upgrade at revsec.revt2d.com\u002Fupgrade |\n| Cron job errors | Ask agent: \"Run the revsec-shield setup\" to recreate cron job |\n| No WhatsApp alerts | Send a message to OpenClaw from WhatsApp first to establish session |\n| `registered_skills` missing | Cron will auto-fix on next run — no action needed |\n| Setup re-runs every time | Check state file has `\"setup_complete\": true` |\n\n---\n\n## What RevSec Shield does NOT do\n\n- It does not change any OpenClaw settings or configuration\n- It does not access any data beyond what the agent config exposes\n- It does not store any data locally beyond `~\u002F.openclaw\u002Frevsec-state.json`\n- It does not send prompts or conversation content to RevSec — only metadata\n- It does not block or modify LLM calls directly — it monitors agent\n  configuration and behaviour via the RevSec API\n- It does not initiate WhatsApp sessions — user must send first message\n\n---\n\n## Cron job reference\n\n| Job name | Schedule | Purpose |\n|---|---|---|\n| `revsec:alert-poll` | `*\u002F5 * * * *` | Auto-detect config changes + poll for threats |\n\nUse `openclaw cron list` to verify the job is registered.\nUse `openclaw cron runs revsec:alert-poll` to see recent run history.\n\n---\n\n## Release notes\n\n**v1.0.0** — Initial public release\n- Agent registration and monitoring\n- 5-minute background polling\n- WhatsApp alert delivery\n- Automatic config change detection\n- New integration alerts\n- Personal security dashboard at revsec.revt2d.com\u002Fpersonal\n\n---\n\n## Links\n\n- Dashboard: https:\u002F\u002Frevsec.revt2d.com\u002Fpersonal\n- Free signup: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\n- Team plan: https:\u002F\u002Frevsec.revt2d.com\u002Fsignup\u002Fteam\n- Support: hello@revupai.com\n\n---\n\n## Publisher\n\n- **Publisher:** @RevUp-AI\n- **Homepage:** https:\u002F\u002Frevsec.revt2d.com\n- **Support:** hello@revupai.com\n- **GitHub:** https:\u002F\u002Fgithub.com\u002FRevUp-AI\u002Frevsec-shield",{"name":5,"homepage":24,"metadata":25,"description":31},"https:\u002F\u002Frevsec.revt2d.com",{"openclaw":26},{"emoji":27,"requires":28,"primaryEnv":30},"🛡️",{"env":29},[30],"REVSEC_API_KEY","24\u002F7 security monitoring for your OpenClaw agent. Detects prompt injection attacks, malicious skills, and data exfiltration attempts. Delivers plain-English alerts to your WhatsApp when something suspicious is detected. Use when the user asks about agent security, wants to check for threats, asks what RevSec detected, or when running setup for the first time. Also handles the 5-minute background security poll (cron job revsec:alert-poll).\n","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fr\u002Frevsec-shield",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill revsec-shield",{"tool":47,"command":48},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill revsec-shield",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill revsec-shield","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fr\u002Frevsec-shield\u002FSKILL.md",true,[],[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]