agents-md-generator
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of Markdown instructions and templates designed to guide an AI agent in documenting a codebase. No executable scripts (Python, Node.js, Shell, etc.) are included in the skill definition.
- [PROMPT_INJECTION] (SAFE): No patterns of prompt injection, role-play bypass, or system prompt extraction were found. The instructions are focused solely on the task of documentation generation.
- [DATA_EXFILTRATION] (SAFE): There are no network operations or sensitive file access patterns. The skill actually promotes security by including a 'Security & Secrets' section in its generated templates to warn against committing credentials.
- [COMMAND_EXECUTION] (SAFE): The skill includes documentation templates that mention standard development commands (such as
pnpm install,rg, andfind). However, the skill itself does not execute these commands or instruct the agent to execute them without user intent.
Audit Metadata