agents-md-generator
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted repository files to generate guidance for agents, creating an opportunity for indirect prompt injection where adversarial content in documentation could influence future agent behavior.
- Ingestion points: The skill reads various repository files including
README.md,CLAUDE.md,CONTRIBUTING.md, and CI workflows (as specified inSKILL.mdandreferences/inspection-and-content-checklist.md). - Boundary markers: The instructions do not specify the use of delimiters or protective headers to isolate the content of the files being processed from the agent's internal instructions.
- Capability inventory: The skill utilizes file reading and writing tools to inspect the environment and produce the
AGENTS.mdfile. - Sanitization: No sanitization or validation steps are described to filter or escape instructions found within the repository's documentation.
Audit Metadata