agents-md
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
- [SAFE]: The skill provides guidelines for generating and maintaining high-signal project documentation for AI agents, focusing on brevity and project-specific accuracy.
- [COMMAND_EXECUTION]: The skill instructions include creating a symbolic link (ln -s AGENTS.md CLAUDE.md). This is a standard and benign file system operation used for documentation consistency across agent platforms.
- [DATA_EXFILTRATION]: The skill identifies and reads local configuration files such as package.json and .eslintrc to populate documentation with relevant commands. This data is processed locally within the project context with no external network transmission.
Audit Metadata