[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M783QRTKEDDHF3W040W7CWSP":3,"skill-same:01M783QRTKEDDHF3W040W7CWSP":137},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M783QRTKEDDHF3W040W7CWSP","cybersecurity",null,"OSS-only security for OWASP Top 10, pentest, vuln testing (XSS, SSRF, CSRF, business-logic, Host header), threat modeling (STRIDE, ATT&CK), Sigma rules, SAST, code audit, AI\u002FLLM red-team, or replacing paid tools (Burp, Nessus, Splunk) with OSS.","aibizmod\u002Faibizmod-service-web","aibizmod","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F295315630?v=4","01M7836CB8EQY701YQ7N88M591","01M7836CBVPZGNSJ8BRP2BT398",0,"MIT","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: cybersecurity\ndescription: OSS-only security for OWASP Top 10, pentest, vuln testing (XSS, SSRF, CSRF, business-logic, Host header), threat modeling (STRIDE, ATT&CK), Sigma rules, SAST, code audit, AI\u002FLLM red-team, or replacing paid tools (Burp, Nessus, Splunk) with OSS.\nlicense: MIT\nmetadata:\n  keywords:\n    - owasp\n    - pentest\n    - vulnerability\n    - xss\n    - ssrf\n    - csrf\n    - business-logic\n    - host-header\n    - open-redirect\n    - forced-browsing\n    - threat-modeling\n    - stride\n    - pasta\n    - vast\n    - mitre-att-and-ck\n    - sigma\n    - sast\n    - code-audit\n    - dalfox\n    - owasp-zap\n    - ffuf\n    - nuclei\n    - interactsh\n    - mitmproxy\n    - semgrep\n    - detection-engineering\n    - incident-response\n    - ai-security\n    - llm-red-team\n    - prompt-injection\n---\n\n# Cybersecurity\n\n## Overview\n\nOSS-only unified cybersecurity skill: analyze, test, and harden software security using **exclusively open-source tooling**. Covers threat modeling, web-vulnerability testing (XSS, business logic, Host header, open redirect, forced browsing), SAST \u002F code audit, AI\u002FLLM-app security, and detection engineering (Sigma + MITRE ATT&CK).\n\nPaid tools (Burp Suite, Nessus, Splunk, CrowdStrike, SonarQube, DOM Invader, Hackvertor) appear only as \"if you already have it\" notes — never as the primary path. For the full paid→OSS swap table, SEE: `references\u002Foss-tool-map.md`.\n\nThis skill fills a gap in this repo: the 5 existing defensive plugins (`csrf-protection`, `xss-prevention`, `vulnerability-scanning`, `security-headers-configuration`, `defense-in-depth-validation`) tell you how to *fix* — this skill tells you how to *find, analyze, and threat-model*.\n\n## When to use\n\nUse this skill whenever the user's task touches software security. Triggers include:\n\n- Web\u002FAPI vulnerability testing (XSS, business logic, Host header, open redirect, forced browsing, SSRF, CSRF).\n- Code audit \u002F SAST \u002F secure-code review (any language).\n- Threat modeling (STRIDE \u002F PASTA \u002F VAST), MITRE ATT&CK mapping, attack-surface analysis.\n- Incident analysis and response reasoning (ransomware, breach, anomaly triage).\n- Detection engineering: Sigma rules, MITRE ATT&CK coverage \u002F gap analysis, ATT&CK Navigator layers.\n- AI \u002F LLM application security (prompt injection, OWASP LLM Top 10, agent safety, \"vibe-coded\" app audits).\n- Compliance work (OWASP, CVE, GDPR \u002F SOC2 \u002F ISO27001).\n- Replacing a paid security tool with an OSS alternative.\n- Mapping a finding to a remediation pattern (cross-references the 5 defensive plugins).\n\n**When NOT to use:**\n\n- IT\u002Finfrastructure-only security operations (patching servers, firewall rules — see ORCHESTRATION exclusions).\n- Malware analysis \u002F reverse engineering of binaries (out of scope).\n- Smart-contract \u002F blockchain security beyond agent-safety review (Solana-specific skills excluded).\n- Anything involving the user's permanently-excluded topics: malware, virus, supabase, openclaw, linux hardening, hardware spoofing, firewall config.\n\n## Execution model — router + dispatcher (NOT an executor)\n\n**This skill is a ROUTER and DISPATCHER.** The main context stays a thin orchestrator (~this file). For every reference doc below, the orchestrator **dispatches a dedicated sub-agent** with the user's task and the matching reference doc as its briefing. The main context **never** inlines a reference doc's body.\n\n### Sub-agent dispatch contract\n\nFor each delegated task, the orchestrator:\n\n1. **(If live-target)** Confirms the authorization gate has been acked for this target this session — see §\"Authorization gate\" below.\n2. **Dispatches a sub-agent** with:\n   - **task:** the user's verbatim task plus any collected context (code, URLs, target scope, ack state).\n   - **briefing:** the contents of the matching `references\u002F\u003Cdoc>.md`.\n   - **model:** the **highest reasoning tier available** — preferred `gpt-5.6 sol` (pinned); fallback `claude-opus-4.x max` or `opus 5 max`. Pin the model + reasoning effort explicitly at dispatch (e.g. `model: \"claude-opus-5-max\"`, `reasoning_effort: \"max\"`). If neither tier is available, use the highest available tier and note the degradation in the dispatch log. Deep adversarial security reasoning needs the high tier — do not leave it to defaults.\n   - **tools:** the reference doc names which OSS tools the sub-agent may invoke.\n   - **return:** the reference doc's `## Sub-agent return contract` defines the output shape.\n3. **Relays the sub-agent's output to the user verbatim** — do not summarize away severity, evidence, or remediation detail.\n4. **(If live-target)** Does not auto-dispatch follow-up live-target tasks without re-confirming scope.\n\n### Fan-out for \"audit everything\" requests\n\nWhen the user asks for broad coverage (\"audit this codebase for security issues\", \"test this app for everything\"), the orchestrator dispatches multiple sub-agents **in parallel** (single message, multiple dispatch tool calls) per `superpowers:dispatching-parallel-agents`:\n\n- code-audit sub-agent (`references\u002Faradotso-code-audit.md`)\n- XSS sub-agent (`references\u002Ftesting-xss.md`) — only if a web app\n- business-logic sub-agent (`references\u002Ftesting-business-logic.md`) — only if a stateful app\n- AI-app sub-agent (`references\u002Faradotso-ai-security.md`) — only if an LLM app\n- (etc.)\n\nThe authorization gate fires **once up front** for the batch (covering all live-target sub-agents in the batch), not per sub-agent. The orchestrator merges all sub-agent outputs into a single report.\n\n### What stays in the main context (never delegated)\n\n| Stays inline | Why |\n|---|---|\n| Routing decision (which reference matches this task) | Cheap; needs full task context. |\n| Authorization gate (`references\u002Fauthorization-disclaimer.md`) | **Safety-critical.** The gate must fire *before* any sub-agent dispatch for live-target tasks. Delegating it would create a TOCTOU window where a sub-agent runs against a real host before ack is confirmed. |\n| Ack-state tracking (per-session, per-target-scope) | Small; must persist across the session's sub-agent calls. |\n| Sub-agent dispatch + result relay | That is the orchestrator's whole job. |\n\n## Authorization gate (live-target tasks only)\n\nThis skill uses OSS offensive tooling (ffuf, nuclei, OWASP ZAP, dalfox, interact.sh, mitmproxy). Running these against a **real host** requires user authorization.\n\n**Static work — NO gate:** code review, SAST, threat modeling, secure-design review, detection-rule authoring, OSS tool installation and template\u002Fhelp reading (e.g., `nuclei --help`, `nuclei -templates-update`, installing binaries), reference lookup. These are **always-allowed** (Track A). Proceed immediately.\n\n**Live-target work — GATED (Track B):** any task that sends requests to a real URL\u002FIP\u002Fhost (`ffuf`, `nuclei`, `zap`, `dalfox`, `interact.sh`, crafted curl to non-localhost). **INVOKING a tool against a URL is Track B, even if framed as \"setup\" or \"configuration.\"** interact.sh server start, mitmproxy transparent mode, nuclei\u002Fffuf\u002Fzap\u002Fdalfox with a URL argument — all are live-target actions requiring the gate. When the user asks the agent to test a real target:\n\n1. **Evaluate the gate IN THIS MAIN CONTEXT** — load `SEE: references\u002Fauthorization-disclaimer.md` and render it to the user.\n2. **Wait for explicit acknowledgement** (\"yes\", \"i confirm\", \"ack\").\n3. **Proceed only after ack.** No ack → no live-target action.\n4. **Ack is per-session and per-target-scope.** Ack for `staging.example.com` does not authorize `prod.example.com`. Re-confirm when the target materially changes.\n5. **Sub-agents receive `ack_state: confirmed` and `target_scope: [...]` as inputs** and **refuse** if missing or out-of-scope. **NOTE: the sub-agent `ack_state` check is NOT defense in depth — it is the same control (main-context gate) expressed a second time in text. There is no signature, shared secret, or independent ground truth the sub-agent can verify. The main-context gate is the real and only authorization control. Do not rely on the sub-agent check in the threat model.**\n6. **The gate is NEVER delegated to a sub-agent.** It runs in main context, *before* dispatch (decision #5 safety invariant).\n\nIf the user declines, or the target is on the gate's red-flags list, the orchestrator **stops**, explains why, and offers Track A alternatives (static review, threat model, etc.).\n\n**Red flags — refuse regardless of ack:** DoS \u002F volume-attack requests, credential stuffing against third parties, exfiltration of real user data, government \u002F critical-infrastructure targets, social-engineering targets.\n\n## Routing\n\n```dot\ndigraph cyber_route {\n  rankdir=TB;\n  node [shape=box];\n\n  start [label=\"User security task\" shape=oval];\n  gate  [label=\"Touches a real host?\" shape=diamond];\n  ack   [label=\"Evaluate authorization gate IN MAIN CONTEXT\\n(references\u002Fauthorization-disclaimer.md)\\nget user ack — NEVER delegate\" shape=box];\n\n  classify [label=\"Classify task\\n(pick exactly one reference)\" shape=diamond];\n\n  analytic [label=\"Analysis \u002F threat-model \u002F\\nincident review\"];\n  test     [label=\"Test a vuln class\\n(XSS, business-logic, redirect, host-header, forced-browsing)\"];\n  detect   [label=\"Author \u002F search\\ndetection rules\"];\n  fix      [label=\"Remediation for\\na finding\"];\n  swap     [label=\"Replace a paid tool\\nwith OSS\"];\n  arad     [label=\"Aradotso capability\\n(code audit \u002F AI-app \u002F agent safety \u002F\\ncompliance \u002F web-vuln learning)\"];\n\n  dispatch [label=\"DISPATCH SUB-AGENT\\nmodel = gpt-5.6 sol (preferred, pinned)\\nfallback: opus 5 max \u002F opus-4.x max\\npass: task + reference doc as briefing\" shape=box color=blue fontcolor=blue];\n  relay   [label=\"Relay sub-agent output to user\\n(do NOT summarize away detail)\"];\n\n  start -> gate;\n  gate  -> ack       [label=\"yes\"];\n  gate  -> classify  [label=\"no (static \u002F design)\"];\n  ack   -> classify;\n\n  classify -> analytic [label=\"analyze\"];\n  classify -> test     [label=\"test\"];\n  classify -> detect   [label=\"detect\"];\n  classify -> fix      [label=\"fix\"];\n  classify -> swap     [label=\"swap\"];\n  classify -> arad     [label=\"aradotso capability\"];\n\n  analytic -> dispatch;\n  test     -> dispatch;\n  detect   -> dispatch;\n  fix      -> dispatch;\n  swap     -> dispatch;\n  arad     -> dispatch;\n\n  dispatch -> relay;\n}\n```\n\n### Routing table\n\n| Task phrasing | Dispatch sub-agent with this briefing |\n|---|---|\n| Analyze an incident \u002F threat-model a feature \u002F security architecture review | `SEE: references\u002Fanalyst-reasoning.md` |\n| Test business-logic flaws (price manipulation, race conditions, workflow bypass, privilege escalation) | `SEE: references\u002Ftesting-business-logic.md` |\n| Test XSS (reflected, stored, DOM) | `SEE: references\u002Ftesting-xss.md` |\n| Test Host header injection (password-reset poisoning, cache poisoning, SSRF via Host, vhost bypass, request smuggling) | `SEE: references\u002Ftesting-host-header.md` |\n| Test open redirect (param enumeration, bypass techniques, vuln chaining) | `SEE: references\u002Ftesting-open-redirect.md` |\n| Find unprotected endpoints \u002F forced browsing \u002F auth-enforcement validation | `SEE: references\u002Ftesting-forced-browsing.md` |\n| Author \u002F search detection rules, MITRE ATT&CK coverage \u002F gap analysis, ATT&CK Navigator layer | `SEE: references\u002Fdetections-mcp.md` |\n| Map finding → existing defensive fix in this repo | `SEE: references\u002Fdefensive-cross-refs.md` |\n| Replace a paid security tool (Burp, Nessus, Splunk, SonarQube, etc.) with OSS | `SEE: references\u002Foss-tool-map.md` |\n| Code audit \u002F SAST (Semgrep, multi-agent audit, falsification-based scan, dual-track SAST) | `SEE: references\u002Faradotso-code-audit.md` |\n| Agent \u002F \"vibe-coded\" app safety review (AI-generated apps, agent\u002FMCP-server adversarial review) | `SEE: references\u002Faradotso-agent-safety.md` |\n| Compliance (OWASP, CVE, GDPR \u002F SOC2 \u002F ISO27001, threat modeling, incident response) | `SEE: references\u002Faradotso-compliance.md` |\n| Web\u002FAPI vuln-testing tools + PortSwigger Web Security Academy walkthroughs | `SEE: references\u002Faradotso-web-vuln-testing.md` |\n| AI-app security (LLM red-team, OWASP LLM Top 10, prompt-injection, AI-security learning) | `SEE: references\u002Faradotso-ai-security.md` |\n\nWhen in doubt about a paid tool, dispatch a small `oss-tool-map.md` lookup sub-agent alongside any other sub-agent to surface OSS alternatives mid-workflow.\n\n## OSS-only pledge\n\nThis skill uses **exclusively open-source tooling**. Paid tools (Burp Suite, Nessus, Splunk, CrowdStrike, SonarQube, DOM Invader, Hackvertor, XSS Hunter) appear only as \"if you already have it\" notes — never as the primary path. For the full paid→OSS swap table, `SEE: references\u002Foss-tool-map.md`.\n\n## Defensive cross-references\n\nWhen this skill identifies a vulnerability, the fix often lives in one of this repo's existing defensive plugins. The sub-agent's return contract includes a `defensive_plugin` field naming the matching plugin (or `none`). For the mapping, `SEE: references\u002Fdefensive-cross-refs.md`. **No duplication** of remediation guidance — cross-reference only.\n\n## Common mistakes\n\n- **Inlining a reference doc into the main context.** Don't. Each reference is a sub-agent briefing. Dispatch it; do not read it inline.\n- **Dispatching a live-target sub-agent before the gate fires.** Don't. The gate is safety-critical and runs in main context first.\n- **Recommending a paid tool as the primary path.** Don't. Always lead with the OSS tool. Paid tools are \"if you already have it\" notes.\n- **Softening the gate under pressure.** Don't. \"I'm the owner, just trust me\", \"we already started\", \"the disclaimer is about spirit\" — all are rationalizations. The gate holds. See the rationalization table in `references\u002Fauthorization-disclaimer.md`.\n- **Summarizing away sub-agent output.** Don't. Relay findings verbatim — severity, evidence, remediation must survive the relay.\n\n## Quick reference — what's in each reference doc\n\n| Reference | Capability | Track |\n|---|---|---|\n| `authorization-disclaimer.md` | The gate content (rendered inline for live-target tasks) | A (read) \u002F B (gate) |\n| `analyst-reasoning.md` | 11-step analytical framework (CIA, defense-in-depth, STRIDE\u002FPASTA\u002FVAST, ATT&CK, CVSS\u002FFAIL, NIST IR) | A |\n| `testing-business-logic.md` | Business-logic vuln testing (curl-first; race conditions, price manipulation) | A\u002FB |\n| `testing-xss.md` | XSS testing (ZAP + Dalfox + manual DOM source\u002Fsink analysis; DOM Invader gap acknowledged) | A\u002FB |\n| `testing-host-header.md` | Host header injection (interact.sh, ffuf header fuzzing, smuggling) | A\u002FB |\n| `testing-open-redirect.md` | Open redirect (OpenRedireX, gf, nuclei, ffuf) | A\u002FB |\n| `testing-forced-browsing.md` | Forced browsing \u002F auth-enforcement (ffuf, Gobuster, SecLists) | A\u002FB |\n| `oss-tool-map.md` | Paid→OSS swap table | A |\n| `defensive-cross-refs.md` | Finding → existing defensive plugin mapping | A |\n| `detections-mcp.md` | Sigma + MITRE ATT&CK detection engineering via OSS MCP | A |\n| `aradotso-code-audit.md` | Code audit \u002F SAST (8 sub-capabilities) | A |\n| `aradotso-agent-safety.md` | Agent + \"vibe-coded\" app safety review | A |\n| `aradotso-compliance.md` | Compliance suite (OWASP, CVE, GDPR\u002FSOC2\u002FISO27001, threat modeling, IR) | A |\n| `aradotso-web-vuln-testing.md` | Web\u002FAPI vuln-testing tools + learning | A\u002FB |\n| `aradotso-ai-security.md` | AI-app security (LLM red-team, OWASP LLM Top 10, references) | A |\n\n\"Track\" = A (always-allowed static\u002Fanalytic) \u002F B (live-target gated) \u002F both.\n\n## Never do\n\n- Run any offensive tool against a real host without authorization (gate fires first).\n- Recommend a paid tool as the primary path for any task.\n- Inline a reference doc's body into the main context — dispatch a sub-agent.\n- Summarize away sub-agent output (relay findings verbatim).\n- Edit the 5 existing defensive plugins — cross-reference only.\n- Touch government \u002F critical-infrastructure \u002F social-engineering targets (permanently out of scope).\n- Commit or push — files land in the working tree only; the user reviews and commits.\n","# Cybersecurity\n\n## Overview\n\nOSS-only unified cybersecurity skill: analyze, test, and harden software security using **exclusively open-source tooling**. Covers threat modeling, web-vulnerability testing (XSS, business logic, Host header, open redirect, forced browsing), SAST \u002F code audit, AI\u002FLLM-app security, and detection engineering (Sigma + MITRE ATT&CK).\n\nPaid tools (Burp Suite, Nessus, Splunk, CrowdStrike, SonarQube, DOM Invader, Hackvertor) appear only as \"if you already have it\" notes — never as the primary path. For the full paid→OSS swap table, SEE: `references\u002Foss-tool-map.md`.\n\nThis skill fills a gap in this repo: the 5 existing defensive plugins (`csrf-protection`, `xss-prevention`, `vulnerability-scanning`, `security-headers-configuration`, `defense-in-depth-validation`) tell you how to *fix* — this skill tells you how to *find, analyze, and threat-model*.\n\n## When to use\n\nUse this skill whenever the user's task touches software security. Triggers include:\n\n- Web\u002FAPI vulnerability testing (XSS, business logic, Host header, open redirect, forced browsing, SSRF, CSRF).\n- Code audit \u002F SAST \u002F secure-code review (any language).\n- Threat modeling (STRIDE \u002F PASTA \u002F VAST), MITRE ATT&CK mapping, attack-surface analysis.\n- Incident analysis and response reasoning (ransomware, breach, anomaly triage).\n- Detection engineering: Sigma rules, MITRE ATT&CK coverage \u002F gap analysis, ATT&CK Navigator layers.\n- AI \u002F LLM application security (prompt injection, OWASP LLM Top 10, agent safety, \"vibe-coded\" app audits).\n- Compliance work (OWASP, CVE, GDPR \u002F SOC2 \u002F ISO27001).\n- Replacing a paid security tool with an OSS alternative.\n- Mapping a finding to a remediation pattern (cross-references the 5 defensive plugins).\n\n**When NOT to use:**\n\n- IT\u002Finfrastructure-only security operations (patching servers, firewall rules — see ORCHESTRATION exclusions).\n- Malware analysis \u002F reverse engineering of binaries (out of scope).\n- Smart-contract \u002F blockchain security beyond agent-safety review (Solana-specific skills excluded).\n- Anything involving the user's permanently-excluded topics: malware, virus, supabase, openclaw, linux hardening, hardware spoofing, firewall config.\n\n## Execution model — router + dispatcher (NOT an executor)\n\n**This skill is a ROUTER and DISPATCHER.** The main context stays a thin orchestrator (~this file). For every reference doc below, the orchestrator **dispatches a dedicated sub-agent** with the user's task and the matching reference doc as its briefing. The main context **never** inlines a reference doc's body.\n\n### Sub-agent dispatch contract\n\nFor each delegated task, the orchestrator:\n\n1. **(If live-target)** Confirms the authorization gate has been acked for this target this session — see §\"Authorization gate\" below.\n2. **Dispatches a sub-agent** with:\n   - **task:** the user's verbatim task plus any collected context (code, URLs, target scope, ack state).\n   - **briefing:** the contents of the matching `references\u002F\u003Cdoc>.md`.\n   - **model:** the **highest reasoning tier available** — preferred `gpt-5.6 sol` (pinned); fallback `claude-opus-4.x max` or `opus 5 max`. Pin the model + reasoning effort explicitly at dispatch (e.g. `model: \"claude-opus-5-max\"`, `reasoning_effort: \"max\"`). If neither tier is available, use the highest available tier and note the degradation in the dispatch log. Deep adversarial security reasoning needs the high tier — do not leave it to defaults.\n   - **tools:** the reference doc names which OSS tools the sub-agent may invoke.\n   - **return:** the reference doc's `## Sub-agent return contract` defines the output shape.\n3. **Relays the sub-agent's output to the user verbatim** — do not summarize away severity, evidence, or remediation detail.\n4. **(If live-target)** Does not auto-dispatch follow-up live-target tasks without re-confirming scope.\n\n### Fan-out for \"audit everything\" requests\n\nWhen the user asks for broad coverage (\"audit this codebase for security issues\", \"test this app for everything\"), the orchestrator dispatches multiple sub-agents **in parallel** (single message, multiple dispatch tool calls) per `superpowers:dispatching-parallel-agents`:\n\n- code-audit sub-agent (`references\u002Faradotso-code-audit.md`)\n- XSS sub-agent (`references\u002Ftesting-xss.md`) — only if a web app\n- business-logic sub-agent (`references\u002Ftesting-business-logic.md`) — only if a stateful app\n- AI-app sub-agent (`references\u002Faradotso-ai-security.md`) — only if an LLM app\n- (etc.)\n\nThe authorization gate fires **once up front** for the batch (covering all live-target sub-agents in the batch), not per sub-agent. The orchestrator merges all sub-agent outputs into a single report.\n\n### What stays in the main context (never delegated)\n\n| Stays inline | Why |\n|---|---|\n| Routing decision (which reference matches this task) | Cheap; needs full task context. |\n| Authorization gate (`references\u002Fauthorization-disclaimer.md`) | **Safety-critical.** The gate must fire *before* any sub-agent dispatch for live-target tasks. Delegating it would create a TOCTOU window where a sub-agent runs against a real host before ack is confirmed. |\n| Ack-state tracking (per-session, per-target-scope) | Small; must persist across the session's sub-agent calls. |\n| Sub-agent dispatch + result relay | That is the orchestrator's whole job. |\n\n## Authorization gate (live-target tasks only)\n\nThis skill uses OSS offensive tooling (ffuf, nuclei, OWASP ZAP, dalfox, interact.sh, mitmproxy). Running these against a **real host** requires user authorization.\n\n**Static work — NO gate:** code review, SAST, threat modeling, secure-design review, detection-rule authoring, OSS tool installation and template\u002Fhelp reading (e.g., `nuclei --help`, `nuclei -templates-update`, installing binaries), reference lookup. These are **always-allowed** (Track A). Proceed immediately.\n\n**Live-target work — GATED (Track B):** any task that sends requests to a real URL\u002FIP\u002Fhost (`ffuf`, `nuclei`, `zap`, `dalfox`, `interact.sh`, crafted curl to non-localhost). **INVOKING a tool against a URL is Track B, even if framed as \"setup\" or \"configuration.\"** interact.sh server start, mitmproxy transparent mode, nuclei\u002Fffuf\u002Fzap\u002Fdalfox with a URL argument — all are live-target actions requiring the gate. When the user asks the agent to test a real target:\n\n1. **Evaluate the gate IN THIS MAIN CONTEXT** — load `SEE: references\u002Fauthorization-disclaimer.md` and render it to the user.\n2. **Wait for explicit acknowledgement** (\"yes\", \"i confirm\", \"ack\").\n3. **Proceed only after ack.** No ack → no live-target action.\n4. **Ack is per-session and per-target-scope.** Ack for `staging.example.com` does not authorize `prod.example.com`. Re-confirm when the target materially changes.\n5. **Sub-agents receive `ack_state: confirmed` and `target_scope: [...]` as inputs** and **refuse** if missing or out-of-scope. **NOTE: the sub-agent `ack_state` check is NOT defense in depth — it is the same control (main-context gate) expressed a second time in text. There is no signature, shared secret, or independent ground truth the sub-agent can verify. The main-context gate is the real and only authorization control. Do not rely on the sub-agent check in the threat model.**\n6. **The gate is NEVER delegated to a sub-agent.** It runs in main context, *before* dispatch (decision #5 safety invariant).\n\nIf the user declines, or the target is on the gate's red-flags list, the orchestrator **stops**, explains why, and offers Track A alternatives (static review, threat model, etc.).\n\n**Red flags — refuse regardless of ack:** DoS \u002F volume-attack requests, credential stuffing against third parties, exfiltration of real user data, government \u002F critical-infrastructure targets, social-engineering targets.\n\n## Routing\n\n```dot\ndigraph cyber_route {\n  rankdir=TB;\n  node [shape=box];\n\n  start [label=\"User security task\" shape=oval];\n  gate  [label=\"Touches a real host?\" shape=diamond];\n  ack   [label=\"Evaluate authorization gate IN MAIN CONTEXT\\n(references\u002Fauthorization-disclaimer.md)\\nget user ack — NEVER delegate\" shape=box];\n\n  classify [label=\"Classify task\\n(pick exactly one reference)\" shape=diamond];\n\n  analytic [label=\"Analysis \u002F threat-model \u002F\\nincident review\"];\n  test     [label=\"Test a vuln class\\n(XSS, business-logic, redirect, host-header, forced-browsing)\"];\n  detect   [label=\"Author \u002F search\\ndetection rules\"];\n  fix      [label=\"Remediation for\\na finding\"];\n  swap     [label=\"Replace a paid tool\\nwith OSS\"];\n  arad     [label=\"Aradotso capability\\n(code audit \u002F AI-app \u002F agent safety \u002F\\ncompliance \u002F web-vuln learning)\"];\n\n  dispatch [label=\"DISPATCH SUB-AGENT\\nmodel = gpt-5.6 sol (preferred, pinned)\\nfallback: opus 5 max \u002F opus-4.x max\\npass: task + reference doc as briefing\" shape=box color=blue fontcolor=blue];\n  relay   [label=\"Relay sub-agent output to user\\n(do NOT summarize away detail)\"];\n\n  start -> gate;\n  gate  -> ack       [label=\"yes\"];\n  gate  -> classify  [label=\"no (static \u002F design)\"];\n  ack   -> classify;\n\n  classify -> analytic [label=\"analyze\"];\n  classify -> test     [label=\"test\"];\n  classify -> detect   [label=\"detect\"];\n  classify -> fix      [label=\"fix\"];\n  classify -> swap     [label=\"swap\"];\n  classify -> arad     [label=\"aradotso capability\"];\n\n  analytic -> dispatch;\n  test     -> dispatch;\n  detect   -> dispatch;\n  fix      -> dispatch;\n  swap     -> dispatch;\n  arad     -> dispatch;\n\n  dispatch -> relay;\n}\n```\n\n### Routing table\n\n| Task phrasing | Dispatch sub-agent with this briefing |\n|---|---|\n| Analyze an incident \u002F threat-model a feature \u002F security architecture review | `SEE: references\u002Fanalyst-reasoning.md` |\n| Test business-logic flaws (price manipulation, race conditions, workflow bypass, privilege escalation) | `SEE: references\u002Ftesting-business-logic.md` |\n| Test XSS (reflected, stored, DOM) | `SEE: references\u002Ftesting-xss.md` |\n| Test Host header injection (password-reset poisoning, cache poisoning, SSRF via Host, vhost bypass, request smuggling) | `SEE: references\u002Ftesting-host-header.md` |\n| Test open redirect (param enumeration, bypass techniques, vuln chaining) | `SEE: references\u002Ftesting-open-redirect.md` |\n| Find unprotected endpoints \u002F forced browsing \u002F auth-enforcement validation | `SEE: references\u002Ftesting-forced-browsing.md` |\n| Author \u002F search detection rules, MITRE ATT&CK coverage \u002F gap analysis, ATT&CK Navigator layer | `SEE: references\u002Fdetections-mcp.md` |\n| Map finding → existing defensive fix in this repo | `SEE: references\u002Fdefensive-cross-refs.md` |\n| Replace a paid security tool (Burp, Nessus, Splunk, SonarQube, etc.) with OSS | `SEE: references\u002Foss-tool-map.md` |\n| Code audit \u002F SAST (Semgrep, multi-agent audit, falsification-based scan, dual-track SAST) | `SEE: references\u002Faradotso-code-audit.md` |\n| Agent \u002F \"vibe-coded\" app safety review (AI-generated apps, agent\u002FMCP-server adversarial review) | `SEE: references\u002Faradotso-agent-safety.md` |\n| Compliance (OWASP, CVE, GDPR \u002F SOC2 \u002F ISO27001, threat modeling, incident response) | `SEE: references\u002Faradotso-compliance.md` |\n| Web\u002FAPI vuln-testing tools + PortSwigger Web Security Academy walkthroughs | `SEE: references\u002Faradotso-web-vuln-testing.md` |\n| AI-app security (LLM red-team, OWASP LLM Top 10, prompt-injection, AI-security learning) | `SEE: references\u002Faradotso-ai-security.md` |\n\nWhen in doubt about a paid tool, dispatch a small `oss-tool-map.md` lookup sub-agent alongside any other sub-agent to surface OSS alternatives mid-workflow.\n\n## OSS-only pledge\n\nThis skill uses **exclusively open-source tooling**. Paid tools (Burp Suite, Nessus, Splunk, CrowdStrike, SonarQube, DOM Invader, Hackvertor, XSS Hunter) appear only as \"if you already have it\" notes — never as the primary path. For the full paid→OSS swap table, `SEE: references\u002Foss-tool-map.md`.\n\n## Defensive cross-references\n\nWhen this skill identifies a vulnerability, the fix often lives in one of this repo's existing defensive plugins. The sub-agent's return contract includes a `defensive_plugin` field naming the matching plugin (or `none`). For the mapping, `SEE: references\u002Fdefensive-cross-refs.md`. **No duplication** of remediation guidance — cross-reference only.\n\n## Common mistakes\n\n- **Inlining a reference doc into the main context.** Don't. Each reference is a sub-agent briefing. Dispatch it; do not read it inline.\n- **Dispatching a live-target sub-agent before the gate fires.** Don't. The gate is safety-critical and runs in main context first.\n- **Recommending a paid tool as the primary path.** Don't. Always lead with the OSS tool. Paid tools are \"if you already have it\" notes.\n- **Softening the gate under pressure.** Don't. \"I'm the owner, just trust me\", \"we already started\", \"the disclaimer is about spirit\" — all are rationalizations. The gate holds. See the rationalization table in `references\u002Fauthorization-disclaimer.md`.\n- **Summarizing away sub-agent output.** Don't. Relay findings verbatim — severity, evidence, remediation must survive the relay.\n\n## Quick reference — what's in each reference doc\n\n| Reference | Capability | Track |\n|---|---|---|\n| `authorization-disclaimer.md` | The gate content (rendered inline for live-target tasks) | A (read) \u002F B (gate) |\n| `analyst-reasoning.md` | 11-step analytical framework (CIA, defense-in-depth, STRIDE\u002FPASTA\u002FVAST, ATT&CK, CVSS\u002FFAIL, NIST IR) | A |\n| `testing-business-logic.md` | Business-logic vuln testing (curl-first; race conditions, price manipulation) | A\u002FB |\n| `testing-xss.md` | XSS testing (ZAP + Dalfox + manual DOM source\u002Fsink analysis; DOM Invader gap acknowledged) | A\u002FB |\n| `testing-host-header.md` | Host header injection (interact.sh, ffuf header fuzzing, smuggling) | A\u002FB |\n| `testing-open-redirect.md` | Open redirect (OpenRedireX, gf, nuclei, ffuf) | A\u002FB |\n| `testing-forced-browsing.md` | Forced browsing \u002F auth-enforcement (ffuf, Gobuster, SecLists) | A\u002FB |\n| `oss-tool-map.md` | Paid→OSS swap table | A |\n| `defensive-cross-refs.md` | Finding → existing defensive plugin mapping | A |\n| `detections-mcp.md` | Sigma + MITRE ATT&CK detection engineering via OSS MCP | A |\n| `aradotso-code-audit.md` | Code audit \u002F SAST (8 sub-capabilities) | A |\n| `aradotso-agent-safety.md` | Agent + \"vibe-coded\" app safety review | A |\n| `aradotso-compliance.md` | Compliance suite (OWASP, CVE, GDPR\u002FSOC2\u002FISO27001, threat modeling, IR) | A |\n| `aradotso-web-vuln-testing.md` | Web\u002FAPI vuln-testing tools + learning | A\u002FB |\n| `aradotso-ai-security.md` | AI-app security (LLM red-team, OWASP LLM Top 10, references) | A |\n\n\"Track\" = A (always-allowed static\u002Fanalytic) \u002F B (live-target gated) \u002F both.\n\n## Never do\n\n- Run any offensive tool against a real host without authorization (gate fires first).\n- Recommend a paid tool as the primary path for any task.\n- Inline a reference doc's body into the main context — dispatch a sub-agent.\n- Summarize away sub-agent output (relay findings verbatim).\n- Edit the 5 existing defensive plugins — cross-reference only.\n- Touch government \u002F critical-infrastructure \u002F social-engineering targets (permanently out of scope).\n- Commit or push — files land in the working tree only; the user reviews and commits.\n",{"name":5,"license":14,"metadata":23,"description":7},{"keywords":24},[25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],"owasp","pentest","vulnerability","xss","ssrf","csrf","business-logic","host-header","open-redirect","forced-browsing","threat-modeling","stride","pasta","vast","mitre-att-and-ck","sigma","sast","code-audit","dalfox","owasp-zap","ffuf","nuclei","interactsh","mitmproxy","semgrep","detection-engineering","incident-response","ai-security","llm-red-team","prompt-injection","main","9f54582c8b485462d402d7e70feaef34801746b9",".opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web","https:\u002F\u002Fgithub.com\u002Faibizmod","2026-09-24 00:48:11",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add aibizmod\u002Faibizmod-service-web --skill cybersecurity",{"tool":67,"command":68},"bunx","bunx skills add aibizmod\u002Faibizmod-service-web --skill cybersecurity",{"tool":70,"command":71},"pnpm","pnpm dlx skills add aibizmod\u002Faibizmod-service-web --skill cybersecurity","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002FSKILL.md",true,[75,81,85,89,93,97,101,105,109,113,117,121,125,129,133],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fanalyst-reasoning.md","REFERENCE","参考文档",16782,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Fanalyst-reasoning.md",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Faradotso-agent-safety.md",10265,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Faradotso-agent-safety.md",{"path":86,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Faradotso-ai-security.md",9773,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Faradotso-ai-security.md",{"path":90,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Faradotso-code-audit.md",11697,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Faradotso-code-audit.md",{"path":94,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Faradotso-compliance.md",8678,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Faradotso-compliance.md",{"path":98,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Faradotso-web-vuln-testing.md",9036,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Faradotso-web-vuln-testing.md",{"path":102,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fauthorization-disclaimer.md",8488,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Fauthorization-disclaimer.md",{"path":106,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":107,"sourceHtmlUrl":108},"references\u002Fdefensive-cross-refs.md",3661,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Fdefensive-cross-refs.md",{"path":110,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":111,"sourceHtmlUrl":112},"references\u002Fdetections-mcp.md",11248,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Fdetections-mcp.md",{"path":114,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":115,"sourceHtmlUrl":116},"references\u002Foss-tool-map.md",8869,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Foss-tool-map.md",{"path":118,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":119,"sourceHtmlUrl":120},"references\u002Ftesting-business-logic.md",10788,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Ftesting-business-logic.md",{"path":122,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":123,"sourceHtmlUrl":124},"references\u002Ftesting-forced-browsing.md",8682,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Ftesting-forced-browsing.md",{"path":126,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Ftesting-host-header.md",8721,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Ftesting-host-header.md",{"path":130,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Ftesting-open-redirect.md",8066,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Ftesting-open-redirect.md",{"path":134,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":135,"sourceHtmlUrl":136},"references\u002Ftesting-xss.md",13761,"https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fcybersecurity\u002Fskills\u002Fcybersecurity\u002Freferences\u002Ftesting-xss.md",[138,145,152,159,166,173],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":18},"01M7846EAPZWCQ8C6G3AAMMR57","{TODO=lowercase-hyphen-case-name}","[TODO: Write comprehensive description in third-person. Start with \"This skill provides...\" or \"This skill should be used when...\"]\n\n[TODO: Add \"Use when\" scenarios - specific situations where Claude should use this skill]\n\n[TODO: Add keywords - technologies, use cases, error messages that should trigger this skill]","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Ftemplates\u002Fskill-skeleton\u002Fskills\u002Fskill-name\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":18},"01M7846A0WGDKJTDPD5QMHQVFV","zustand-state-management","Zustand state management for React with TypeScript. Use for global state, Redux\u002FContext API migration, localStorage persistence, slices pattern, devtools, Next.js SSR, or encountering hydration errors, TypeScript inference issues, persist middleware problems, infinite render loops.","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fzustand-state-management\u002Fskills\u002Fzustand-state-management\u002FSKILL.md",[],[],{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":158,"publishedAt":18},"01M78463GGSP9B3JSF146B2MG0","zod","TypeScript-first schema validation and type inference. Use for validating API requests\u002Fresponses, form data, env vars, configs, defining type-safe schemas with runtime validation, transforming data, generating JSON Schema for OpenAPI\u002FAI, or encountering missing validation errors, type inference issues, validation error handling problems. Zero dependencies (2kb gzipped).","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fzod\u002Fskills\u002Fzod\u002FSKILL.md",[],[],{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":18},"01M7845ZX17SVNNY7EDGPJHSBT","xss-prevention","XSS attack prevention with input sanitization, output encoding, Content Security Policy. Use for user-generated content, rich text editors, web application security, or encountering stored XSS, reflected XSS, DOM manipulation, script injection errors.","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fxss-prevention\u002Fskills\u002Fxss-prevention\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":18},"01M7845ST1H37YHSXWWQ9N0V0S","wordpress-plugin-core","WordPress plugin development with hooks, security, REST API, custom post types. Use for plugin creation, $wpdb queries, Settings API, or encountering SQL injection, XSS, CSRF, nonce errors.","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fwordpress-plugin-core\u002Fskills\u002Fwordpress-plugin-core\u002FSKILL.md",[],[],{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":18},"01M7845PTWD5HWSTGP35Q8TFNY","woocommerce-dev-cycle","Run tests, linting, and quality checks for WooCommerce development. Use when running tests, fixing code style, or following the development workflow in WooCommerce projects.","https:\u002F\u002Fgithub.com\u002Faibizmod\u002Faibizmod-service-web\u002Fblob\u002Fmain\u002F.opencode\u002Fskill\u002Fclaude-skills\u002Fplugins\u002Fwoocommerce-dev-cycle\u002Fskills\u002Fwoocommerce-dev-cycle\u002FSKILL.md",[],[]]