reviewing-agents-md
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from project manifest files and documentation, which constitutes an attack surface for indirect prompt injection from potentially malicious repositories.\n- Ingestion points: Reads README.md, package.json, pyproject.toml, and other configuration files in the project root (SKILL.md).\n- Boundary markers: The skill does not define explicit delimiters or ignore-instructions for the external content it processes.\n- Capability inventory: The skill is restricted to analyzing files and writing an AGENTS.md file to the local directory.\n- Sanitization: No explicit content sanitization or validation of the input files is described.
Audit Metadata