doc-flow
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scanning files in the
docs/directory and.aidoc/profile.yamlto determine project status and check for template conformance. - Ingestion points: Files located in
docs/and.aidoc/profile.yamlare read to identify active layers and document status. - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the ingested file content.
- Capability inventory: The skill is limited to reading files, reporting progress, and recommending other internal skills (e.g.,
doc-brd,doc-prd). It explicitly states it does not create artifacts itself. - Sanitization: The skill does not perform sanitization on the document content, but its primary function is structural validation (verifying headings) rather than processing logic from the text.
Audit Metadata