design-critique

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions for the AI to perform UX design reviews. No malicious code, credential exposure, or exfiltration patterns were identified.
  • [NO_CODE]: The skill does not include any scripts, dependencies, or executable content. It relies solely on the LLM's reasoning capabilities within the provided instructional framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and evaluate untrusted data shared by users (such as UI code, markup, or text descriptions). While this constitutes an attack surface, the skill does not have access to tools, network operations, or file system modifications that could be used to facilitate an exploit. The risk is minimized as there are no executable sinks for potential injection payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 07:31 AM