agent-md-creator
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository (README, command definitions, CI, and source code) to generate or update AGENTS.md files, creating a surface for indirect prompt injection.
- Ingestion points: The skill instructs the agent to inspect the README, command definitions, CI, and code to establish facts for the documentation.
- Boundary markers: The instructions do not define boundary markers or delimiters to differentiate between repository data and instructions when processing these files.
- Capability inventory: The skill's primary capability is to write and modify files within the repository.
- Sanitization: No sanitization, escaping, or validation of the repository content is mentioned before it is used to draft the operational contract.
Audit Metadata