web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, potentially untrusted source code and project documentation. Maliciously crafted instructions within these files could attempt to influence the agent's behavior.
  • Ingestion points: Target source files provided by the user and the SCSS styling guide (docs/project-reference/scss-styling-guide.md).
  • Boundary markers: The skill does not define clear delimiters or provide instructions to the agent to ignore potentially malicious content within the files it reviews.
  • Capability inventory: The skill is configured to use Read, Grep, Glob, and Bash tools for its workflow.
  • Sanitization: There is no evidence of sanitization or input validation for the content read from the target files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 11:22 AM
Security Audit — agent-trust-hub — web-design-guidelines