web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill fetches guidelines from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md before each run.
  • Evidence: The URL belongs to the vercel-labs GitHub organization, which is explicitly listed as a Trusted External Source.
  • [TRUST-SCOPE-RULE]: Per the security policy, downloads from trusted sources are downgraded to LOW/SAFE. No malicious behavior was detected in the skill's handling of this data.
  • [COMMAND_EXECUTION] (SAFE): The skill reads local files based on user-provided patterns.
  • Evidence: The file reading is limited to the arguments provided by the user for the purpose of UI auditing.
  • [PROMPT_INJECTION] (LOW): Indirect Prompt Injection surface via external guidelines.
  • Evidence: The skill ingests remote Markdown content and treats it as 'rules' for the LLM to follow.
  • Risk Assessment: While this is a theoretical attack vector, the use of a Trusted External Source (Vercel) significantly mitigates the risk of malicious instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM