agents-md-generator
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data from the local project environment to generate documentation.
- Ingestion points: The skill reads
README.md, existingAGENTS.mdfiles, and.nextstage-harness/manifest.jsonfrom the repository root to gather context. - Boundary markers: There are no explicit instructions or delimiters used when reading these files to warn the agent against following instructions embedded within them.
- Capability inventory: The skill possesses file-write capabilities, specifically targeting
{product_root}/AGENTS.mdand{product_root}/CLAUDE.md. - Sanitization: The skill lacks explicit sanitization or validation of the content gathered during its reconnaissance phase before interpolating it into the generated documentation templates.
Audit Metadata