design-system

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose involves reviewing user-provided interface code and design implementations, which introduces an indirect prompt injection surface where malicious instructions could be embedded in the data processed by the agent.
  • Ingestion points: The skill accepts user-supplied UI code or interface descriptions for review as indicated in the 'Example' section of SKILL.md.
  • Boundary markers: Absent. There are no instructions for the agent to use delimiters or specific warnings to ignore instructions embedded within the user data.
  • Capability inventory: No dangerous capabilities such as subprocess execution, file system writes, or network requests are identified within the skill's own content.
  • Sanitization: Absent. The instructions do not specify any validation or sanitization of the input content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 04:53 PM
Security Audit — agent-trust-hub — design-system