maintain-agents-md
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted repository data, creating a potential surface for instructions embedded in code or manifests to influence the agent.\n
- Ingestion points: The skill reads instruction chains, manifests, CI commands, scripts, and repository code (SKILL.md, references/format-and-evidence.md).\n
- Boundary markers: There are no instructions defining the use of delimiters or 'ignore' headers to separate repository content from the agent's core task instructions.\n
- Capability inventory: The agent has the authority to read files from the filesystem and write new AGENTS.md files.\n
- Sanitization: The skill documentation does not provide guidelines for sanitizing or escaping the data read from external repository files before processing.
Audit Metadata