critique-affordance
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, credentials, or persistent mechanisms detected. The skill instructions focus strictly on UI/UX critique.
- [NO_CODE]: The skill contains only markdown instructions and no executable scripts, reducing the direct attack surface.
- [PROMPT_INJECTION]: The skill processes untrusted external data (UI screens), creating a potential for indirect prompt injection if those screens contain malicious text.
- Ingestion points: Screen content described in SKILL.md.
- Boundary markers: None present to distinguish UI text from instructions.
- Capability inventory: Limited to generating design feedback and ratings.
- Sanitization: None provided for analyzed content.
Audit Metadata