brain-to-docs
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns detected. The skill's operations are limited to reading and writing documentation files (README.md and ADRs) within the project directory.
- [PROMPT_INJECTION]: The skill reads existing documentation which could serve as an attack surface for indirect prompt injection if those files contain instructions from untrusted sources. However, as this is essential for its primary documentation-maintenance purpose, it is considered a standard operational risk rather than a malicious finding.
- Ingestion points: Reads README.md and files in docs/adr/ during the initialization step of the interview loop.
- Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands in the source files.
- Capability inventory: File system write access for updating README.md and creating markdown files in docs/adr/.
- Sanitization: No content validation or instruction filtering is performed on the ingested documentation.
Audit Metadata