skills/shinpr/nautilus/recipe-vision/Gen Agent Trust Hub

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
Risk Level
SAFE
Analyzed
Sep 22, 2026, 01:09 PM
Security Audit — agent-trust-hub — recipe-vision