agents-md
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: This skill follows research-backed best practices for creating minimal documentation to improve AI agent performance. It performs routine analysis of project structures and generates markdown files, posing no threat to the user or system.
- [COMMAND_EXECUTION]: The skill includes instructions to create a symbolic link (
ln -s AGENTS.md CLAUDE.md). This is a common and safe administrative task for project documentation setup. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) by design, as it interprets local project files to generate agent instructions.
- Ingestion points: Project metadata files such as
package.json, lock files, and linter configurations. - Boundary markers: None identified; the skill relies on the agent to interpret configuration context without specific delimiters.
- Capability inventory: Local file system read and write access for documentation maintenance.
- Sanitization: None; the skill assumes configuration files are legitimate sources for documentation content.
Audit Metadata