recipe-vision
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by processing external data from the project workspace to generate or update strategic documents.
- Ingestion points: The skill reads from docs/product/learnings.md in Step 2 of the Execution Decision Flow and accepts user-supplied text during context assessment.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to separate untrusted file content from the agent's core task logic.
- Capability inventory: The skill has the capability to write and update markdown files (docs/product/vision.md and docs/product/design-principles.md) in Step 5.
- Sanitization: There is no evidence of input validation, filtering, or escaping of the ingested content before it is interpolated into the final vision draft.
Audit Metadata