concept-prd
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting external data and performing file operations.
- Ingestion points: The transcription workflow in
SKILL.mdinvolves reading external model definitions, requirement sources, and existing project documents. - Boundary markers: There are no instructions defining delimiters or explicit guidelines for the agent to ignore instructions that might be embedded within the input documents.
- Capability inventory: The skill has the capability to write and update Markdown files within the repository (e.g.,
docs/prd/README.md,CONCEPT.md,SYNCS.md). - Sanitization: The instructions do not specify any validation, filtering, or escaping of the content ingested from external sources before it is written to the output files.
Audit Metadata