agents-skill-security-audit
por cerbug45
CLI UtilitiesResumo
Minimal helper to audit skill.md-style instructions for supply-chain risks.
Descrição
O que esta skill faz
Scans skill.md-style instruction files for supply-chain risks using heuristic pattern matching. It flags exfiltration patterns such as HTTP POST requests, curl calls to unknown domains, reads of sensitive files like ~/.env, and credential keywords. Output is a markdown report with a risk level.
It targets the specific structure of skill.md instruction files rather than running generic secrets scanning, so it catches context-aware patterns like credential reads embedded in agent prompts.
Quando usá-la
- Checking a third-party skill file before installing it
- Auditing new agent instructions added to a shared team repo
- Scanning downloaded SKILL.md files before running them locally
- Adding a skill file check to a CI pipeline before merging
- Spot-checking an AI agent prompt file for credential leaks
Exemplo de fluxo de trabalho
User asks: audit this skill.md for supply-chain risks
- 1
Receives the path to the skill.md file
- 2
Runs audit.py against the file using heuristic pattern matching
- 3
Scans for HTTP POST calls, curl to unknown domains, ~/.env reads, and credential keywords
- 4
Builds a permission manifest listing filesystem and network touches found
- 5
Outputs a markdown summary with an overall risk level
Markdown report listing flagged patterns and an overall risk level rating
Instalação
clawhub install cerbug45/agents-skill-security-auditExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.