agentic-security
/agentic-security
Audytuje bezpieczeństwo konfiguracji agenta AI w repozytorium: ustawienia, hooki, serwery MCP, skille i sekrety.
- Autor
- fusengine ↗
- Repozytorium
- agents ↗
- Licencja
- MIT
- Ostatnia zmiana repozytorium
- 13.11.2026
Ocena i bezpieczeństwo
- Pliki w paczce
- 12
- Skrypty
- 0
- Komentarze HTML
- 0
- Adresy URL w SKILL.md
- 0
Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.
MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.
Co robi i kiedy
Audytuje bezpieczeństwo konfiguracji agenta AI w repozytorium: ustawienia, hooki, serwery MCP, skille i sekrety.
Argumenty
/agentic-security [path] [--scope trust|hooks|mcp|injection|permissions|secrets|ci]
Oryginalny opis (EN)
Use when auditing the security of an AI-coding-agent setup in a repository: Claude Code project settings and hooks, plugin manifests and hooks.json, .mcp.json and MCP servers, skills, agents and rule files, permission rules, secrets in agent configuration, and CI workflows that run an AI agent on pull requests. Do NOT use for application code vulnerabilities (use security-scan), dependency CVEs (use dependency-audit or cve-research), auth flows (use auth-audit) or HTTP headers (use security-headers).
Jak działa
- Overview
- Audit Areas
- Workflow
- Critical Rules
- References
Podgląd SKILL.md
--- name: agentic-security description: "Use when auditing the security of an AI-coding-agent setup in a repository: Claude Code project settings and hooks, plugin manifests and hooks.json, .mcp.json and MCP servers, skills, agents and rule files, permission rules, secrets in agent configuration, and CI workflows that run an AI agent on pull requests. Do NOT use for application code vulnerabilities (use security-scan), dependency CVEs (use dependency-audit or cve-research), auth flows (use auth-audit) or HTTP headers (use security-headers)." argument-hint: "[path] [--scope trust|hooks|mcp|injection|permissions|secrets|ci]" user-invocable: true --- <objective> This skill audits the attack surface that an AI coding agent adds to a repository: files that run code before or around the workspace trust dialog, hooks shipped by plugins, MCP servers and their credentials, prompt-injection paths into the agent's context, permission rules and bypass modes, secrets stored in agent configuration and memory, and CI jobs that run an agent on untrusted input. It reports; it never fixes the audited project and never changes the user's settings. Every finding carries its evidence (file:line), passes a read-only refutation pass, and cites the standard entry it maps to, as read on the source named in the references. </objective> # Agentic Security Skill ## Overview Project configuration for an agent is executable: a `.claude/settings.json` hook, an `.mcp.json` server command or an `env` override runs on the developer's machine. Check Point Research showed this end to end (CVE-2025-59536, CVE-2026-21852). This skill turns the vendor documentation into checklists an auditor can run read-only. ## Audit Areas | Area | What is checked | Reference | |------|-----------------|-----------| | Trust boundary | Hooks, `env`, helpers, MCP auto-approval and base-URL overrides that act before trust | [trust-boundary.md](references/trust-boundary.md) | | Hook supply chain | Plugin `hooks.json`, `plugin.json` `hooks` / `mcpServers` / `userConfig` | [hooks-plugins.md](references/hooks-plugins.md) | | MCP trust | Every server source, publisher, pinning, env and tokens, tool descriptions | [mcp-trust.md](references/mcp-trust.md) | | Prompt injection | Untrusted content reaching the agent, instruction files that obey observed content | [prompt-injection.md](references/prompt-injection.md) | | Permissions | Broad allow rules, deny-rule limits, bypass and auto modes, saved approvals | [permissions.md](references/permissions.md) | | Secrets | Keys and tokens in settings, `.mcp.json`, hooks, memory and lesson files, `.env` | [secrets.md](references/secrets.md) | | CI agents | AI review or agent actions running on untrusted pull requests | [ci-agents.md](references/ci-agents.md) | ## Workflow 1. **Inventory** the agent surface of the target path: `.claude/`, `.mcp.json`, `.claude-plugin/`, `hooks/`, `skills/`, `agents/`, `CLAUDE.md`, rule and memory files, `.github/workflows/`, and the equivalent folders of other agent tools present in the repository. 2. **Run** the checklist of each area in scope ([audit-checklist.md](references/templates/audit-checklist.md)). 3. **Score** each candidate: severity, confidence 1-10, CWE and standard entry from [standards-map.md](references/standards-map.md). 4. **Verify**: run the refutation pass in [verification.md](references/verification.md) on every candidate. Confidence 8 or more becomes a finding; lower goes to "needs manual review". 5. **Report** with [audit-report.md](references/templates/audit-report.md) to `docs/security/YYYY-MM-DD-<scope>.md` inside the audited repository. ## Critical Rules | Rule | Why | |------|-----| | Report only, never fix or change settings | The audit must not alter the trust state it measures | | Never print a secret value | Report file:line and the secret type only | | Read `~/.claude`, `~/.codex` and similar only when the owner asks, and read-only | User-level config is outside the audited repository | | Cite every fact from the reference files | Vendor behavior changes by version; no claim from memory | | A static read never proves exploitability | See [verification.md](references/verification.md) | ## References - [Trust boundary](references/trust-boundary.md) — what a repository can run before trust, the two CVEs - [Hooks and plugins](references/hooks-plugins.md) — plugin hook supply chain - [MCP trust](references/mcp-trust.md) — server inventory and trust checks - [Prompt injection](references/prompt-injection.md) — injection paths into the agent - [Permissions](references/permissions.md) — rules, modes and their documented limits - [Secrets](references/secrets.md) — secrets in agent configuration and memory - [CI agents](references/ci-agents.md) — agents in GitHub Actions - [Standards map](references/standards-map.md) — OWASP LLM / Agentic entries and CWE, as read - [Verification and limits](references/verification.md) — refutation pass, what the skill does not prove - [Audit checklist](references/templates/audit-checklist.md) · [Audit report](references/templates/audit-report.md)
Pliki w paczce (12)
- SKILL.md 5 KB
- references/ci-agents.md 4 KB
- references/hooks-plugins.md 4 KB
- references/mcp-trust.md 4 KB
- references/permissions.md 5 KB
- references/prompt-injection.md 5 KB
- references/secrets.md 4 KB
- references/standards-map.md 4 KB
- references/trust-boundary.md 5 KB
- references/verification.md 4 KB
- references/templates/audit-checklist.md 3 KB
- references/templates/audit-report.md 3 KB
Wersje
W bazie nie ma innych skilli o nazwie agentic-security.
Migawka bazy z 13.11.2026 · wersja paczki 428524f14fe7 (skrót SHA-256 całej paczki)
Pobrania w ostatnich 30 dniach: 0 · ranking
Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.
Podobne skille
- 100security-scan
Skanuje konfigurację Claude Code (katalog .claude/) pod kątem podatności, błędnych konfiguracji i ryzyka wstrzyknięć za pomocą AgentShield: CLAUDE.md, settings.json, serwery MCP, hooki i definicje agentów. - 100security-scan
Skanuje konfigurację .gina: CLAUDE.md, ustawienia, serwery MCP, haki i definicje agentów pod kątem podatności i błędnych ustawień. - 100security-scan
Skanuje konfigurację .nemo: NEMO.md, ustawienia, serwery MCP, haki i definicje agentów pod kątem błędów i wstrzyknięć. - 82security-audit
Skanuje kod pod kątem sekretów, błędów uwierzytelniania, ryzykownych zależności i luk OWASP Top 10. - 90config-security-scan
Sprawdza statycznie konfigurację agenta AI pod kątem błędów bezpieczeństwa w ustawieniach, serwerach MCP i sekretach. - 90security-audit
Przegląda bezpieczeństwo kodu, audytuje zależności pod kątem CVE oraz sprawdza konfigurację, sekrety i wzorce uwierzytelniania.