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
Risk Level
SAFE
Analyzed
Jun 30, 2026, 05:32 PM
Security Audit — agent-trust-hub — critique-affordance