brain-to-docs
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes existing documentation files, which creates an attack surface for indirect prompt injection.\n
- Ingestion points: The instructions require the agent to read
README.mdand thedocs/adr/directory inSKILL.md.\n - Boundary markers: There are no explicit markers or delimiters defined to distinguish ingested file content from the agent's core instructions.\n
- Capability inventory: The skill involves reading and writing markdown files on the local filesystem.\n
- Sanitization: There is no defined process for sanitizing or validating the content retrieved from the documentation files.\n- [NO_CODE]: The skill does not provide any executable scripts or binary files, consisting entirely of markdown-based instructions.
Audit Metadata