designpowers-critique
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data including design briefs, plans, and technical artefacts like code or prototypes.
- Ingestion points: Step 1 requires gathering design artefacts, code, and prototypes for review.
- Boundary markers: The process lacks explicit delimiters or instructions to the agent to disregard embedded directives within the reviewed artefacts.
- Capability inventory: The skill involves reading files and invoking downstream skills like design-debt-tracker to record findings.
- Sanitization: There are no defined mechanisms for sanitizing or validating the content of the external design assets before they are processed by the agent.
Audit Metadata