design-review
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of design descriptions and screen files, which provides an attack surface for indirect prompt injection.
- Ingestion points: As described in
SKILL.md, the skill ingests content from several directories:outputs/screens/,outputs/design-briefs/,context-library/brand/, andcontext-library/personas/. - Boundary markers: The instructions do not define clear delimiters or warning markers to help the agent distinguish between its core instructions and the potentially untrusted content within the design files.
- Capability inventory: The skill's capabilities are limited to reading local design context and writing resulting reviews to
outputs/design-reviews/. No network exfiltration, arbitrary command execution, or remote code patterns were detected. - Sanitization: There is no evidence of sanitization, filtering, or validation of the text data extracted from the ingested design files.
Audit Metadata