[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75N2BVYYGP1B7QDAV2PKVRD":3,"skill-same:01M75N2BVYYGP1B7QDAV2PKVRD":45},{"skillNo":4,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":20,"frontMatter":21,"refName":22,"commitSha":23,"skillDirectory":24,"forksCount":25,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":28,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M75N2BVYYGP1B7QDAV2PKVRD","agentguard",null,"javimosch\u002Fopen-claw-skills","javimosch","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12900508?v=4","01M6D3F2AS6PV75ET9PZ1QGP8J","Javier Leandro Arancibia","01M75B8NCTAJG9WH5YNZH7C3D8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmanas-io-ai\u002Fagentguard\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"# AgentGuard - Security Monitoring Skill\n\n**Version:** 1.0.0  \n**Author:** Manas AI  \n**Category:** Security & Monitoring\n\n## Overview\n\nAgentGuard is a comprehensive security monitoring skill that watches over agent operations, detecting suspicious behavior, logging communications, and providing actionable security reports.\n\n---\n\n## Capabilities\n\n### 1. File Access Monitoring\nTrack all file read\u002Fwrite operations with pattern analysis.\n\n**Trigger:** Continuous background monitoring  \n**Command:** `agentguard monitor files [--watch-dir \u003Cpath>]`\n\n**What it detects:**\n- Unusual file access patterns (bulk reads, sensitive directories)\n- Access to credential files (.env, .secrets, keys)\n- Unexpected write operations to system directories\n- File exfiltration attempts (large reads followed by network calls)\n\n### 2. API Call Detection\nMonitor outbound API calls for suspicious activity.\n\n**Command:** `agentguard monitor api`\n\n**What it detects:**\n- Calls to unknown\u002Funtrusted endpoints\n- Unusual API call frequency (rate anomalies)\n- Sensitive data in request payloads\n- Authentication token exposure\n- Calls to known malicious domains\n\n### 3. Communication Logging\nLog all external communications for audit trails.\n\n**Command:** `agentguard log comms [--output \u003Cpath>]`\n\n**Logs include:**\n- HTTP\u002FHTTPS requests (sanitized)\n- WebSocket connections\n- Email sends\n- Message platform outputs (Telegram, Discord, etc.)\n- Timestamp, destination, payload hash\n\n### 4. Anomaly Detection\nML-lite pattern analysis for behavioral anomalies.\n\n**Command:** `agentguard detect anomalies [--sensitivity \u003Clow|medium|high>]`\n\n**Detection methods:**\n- Baseline deviation (learns normal patterns)\n- Time-of-day anomalies\n- Sequence analysis (unusual operation chains)\n- Volume spikes\n- New destination detection\n\n### 5. Security Reports\nGenerate comprehensive daily security reports.\n\n**Command:** `agentguard report [--period \u003Cdaily|weekly|monthly>]`\n\n**Report includes:**\n- Activity summary\n- Alert breakdown by severity\n- Top accessed resources\n- Communication destinations\n- Anomaly timeline\n- Recommendations\n\n---\n\n## Configuration\n\n### Config File: `config\u002Fagentguard.yaml`\n\n```yaml\nmonitoring:\n  enabled: true\n  file_watch_dirs:\n    - ~\u002Fclawd\n    - ~\u002F.clawdbot\n  exclude_patterns:\n    - \"*.log\"\n    - \"node_modules\u002F**\"\n    - \".git\u002F**\"\n\nalerts:\n  sensitivity: medium  # low, medium, high\n  channels:\n    - telegram\n  alert_on:\n    - credential_access\n    - bulk_file_read\n    - unknown_api_endpoint\n    - data_exfiltration\n  cooldown_minutes: 15\n\napi_monitoring:\n  trusted_domains:\n    - api.anthropic.com\n    - api.openai.com\n    - api.telegram.org\n    - api.elevenlabs.io\n  block_on_suspicious: false  # true = prevent call, false = alert only\n\nlogging:\n  retention_days: 30\n  log_dir: ~\u002F.agentguard\u002Flogs\n  hash_sensitive_data: true\n\nreporting:\n  auto_daily_report: true\n  report_time: \"09:00\"\n  report_channel: telegram\n```\n\n---\n\n## Usage Examples\n\n### Start Full Monitoring\n```\nagentguard start\n```\nEnables all monitoring features with default config.\n\n### Check Current Security Status\n```\nagentguard status\n```\nReturns current threat level, active monitors, recent alerts.\n\n### Investigate Specific Activity\n```\nagentguard investigate --timerange \"last 2 hours\" --type file_access\n```\n\n### Generate Immediate Report\n```\nagentguard report --now\n```\n\n### Review Alert History\n```\nagentguard alerts --last 24h --severity high\n```\n\n### Whitelist a Domain\n```\nagentguard trust add api.newservice.com --reason \"Required for X integration\"\n```\n\n---\n\n## Alert Severity Levels\n\n| Level | Color | Meaning | Example |\n|-------|-------|---------|---------|\n| INFO | 🔵 | Normal logged activity | File read in workspace |\n| LOW | 🟢 | Minor deviation | Slightly elevated API calls |\n| MEDIUM | 🟡 | Notable anomaly | Access to .env file |\n| HIGH | 🟠 | Potential threat | Bulk credential access |\n| CRITICAL | 🔴 | Immediate action needed | Data exfiltration pattern |\n\n---\n\n## Integration Points\n\n### With Clawdbot\n- Receives file\u002FAPI operation hooks\n- Sends alerts via configured channels\n- Integrates with heartbeat for periodic checks\n\n### With Other Skills\n- Shares threat data with other security skills\n- Can block operations (if configured)\n- Provides audit logs for compliance skills\n\n---\n\n## Data Storage\n\n```\n~\u002F.agentguard\u002F\n├── logs\u002F\n│   ├── file_access\u002F\n│   ├── api_calls\u002F\n│   └── communications\u002F\n├── baselines\u002F\n│   └── behavior_model.json\n├── alerts\u002F\n│   └── YYYY-MM-DD.json\n└── reports\u002F\n    └── YYYY-MM-DD_report.md\n```\n\n---\n\n## Privacy & Security\n\n- **No external data transmission** - All processing is local\n- **Sensitive data hashing** - Credentials are never logged in plain text\n- **Configurable retention** - Auto-delete old logs\n- **Encrypted storage** - Optional AES encryption for logs\n\n---\n\n## Troubleshooting\n\n### High false positive rate\n→ Increase baseline learning period or reduce sensitivity\n\n### Missing file events\n→ Check `file_watch_dirs` config covers target directories\n\n### Reports not generating\n→ Verify `report_time` format and timezone settings\n\n---\n\n## Execution Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `execution\u002Fmonitor.py` | Core monitoring daemon |\n| `execution\u002Fdetector.py` | Anomaly detection engine |\n| `execution\u002Flogger.py` | Structured logging handler |\n| `execution\u002Falerter.py` | Alert dispatch system |\n| `execution\u002Freporter.py` | Report generation |\n\n---\n\n## Author Notes\n\nAgentGuard is designed with defense-in-depth principles. It assumes agents can be compromised or manipulated, and provides visibility into their operations.\n\nFor maximum security, run AgentGuard in a separate process with limited write access to prevent a compromised agent from disabling monitoring.\n",{},"main","f9d3fe7cf9ac8f1ea63a0d96e98e1f510a3814db","skills\u002Fmanas-io-ai\u002Fagentguard",1,"https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills","https:\u002F\u002Fgithub.com\u002Fjavimosch","intrane.fr","Building robust, open-source infrastructure for the commons. AI-leveraged, self-hosted, built to last.","2026-06-07 03:34:58",{"source":7,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add javimosch\u002Fopen-claw-skills --skill agentguard",{"tool":37,"command":38},"bunx","bunx skills add javimosch\u002Fopen-claw-skills --skill agentguard",{"tool":40,"command":41},"pnpm","pnpm dlx skills add javimosch\u002Fopen-claw-skills --skill agentguard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmanas-io-ai\u002Fagentguard\u002FSKILL.md",true,[],[46,54,61,68,75,82],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":53},"01M778GGXG2VQ0YF31W2MKGMQZ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":53},"01M778G7BH8SBJ9FJ6C3G7CB1K","ceaser","Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir\u002FUltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":53},"01M778FYCJQZWFKKX5FYMK3S47","ceaser-send","Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp \u003Csubcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir\u002FUltraHonk zero-knowledge proofs.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyra-v21\u002Fceaser-send\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":53},"01M778FQQNSEYA3HJKZBPQ4M9Z","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":53},"01M778FGVZX7QA2TF9BFMM37FY","moldium","Post and manage content on the Moldium blog platform. Triggered by \"post to Moldium\", \"write a blog post\", \"publish an article\", etc.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzyom45\u002Fmoldium\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":53},"01M778F88D8PQ9MQ0KNW2TJ8ZH","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http:\u002F\u002Fweakaccept.top:8000\u002F.","https:\u002F\u002Fgithub.com\u002Fjavimosch\u002Fopen-claw-skills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[],[]]