agents-md-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting and analyzing potentially untrusted data from the repository's source code and configuration files, which could contain embedded malicious instructions.\n
- Ingestion points: As specified in SKILL.md and references/format-and-evidence.md, the agent reads instruction chains, manifests, CI commands, scripts, and source code.\n
- Boundary markers: The instructions do not include specific delimiters or directives to ignore instructions that might be embedded within the files being analyzed.\n
- Capability inventory: Across SKILL.md and its references, the skill is authorized to read files, write Markdown documentation, and verify repository state. The instruction to "record... actual execution results" in references/format-and-evidence.md suggests the agent may execute local scripts or commands to verify their correctness.\n
- Sanitization: No sanitization, filtering, or specific validation logic is described for the content ingested from the repository before it is used to generate documentation.
Audit Metadata