find-gaps
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external, untrusted artifacts (stories, plans, specs, mocks) provided by users. This creates a surface for indirect prompt injection where instructions embedded in the artifacts could attempt to manipulate the agent.
- Ingestion points: The skill reads user-provided artifacts to perform gap analysis (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or specific instructions to ignore embedded prompts within the reviewed artifacts.
- Capability inventory: The skill is instructed to write confirmed updates back to the source documents (files, canvas, or docs).
- Sanitization: The skill incorporates a robust mitigation strategy by requiring a conversational loop where every proposed artifact update must be shown to the user for explicit confirmation (write as-is / edit inline / discard) before execution.
Audit Metadata