web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository to serve as the rule set for auditing user files.
  • [PROMPT_INJECTION]: The skill design includes an indirect prompt injection surface as it integrates untrusted data into its instruction set.
  • Ingestion points: Reads external rules from a remote Markdown file (command.md) and processes the content of user-provided local files.
  • Boundary markers: There are no defined boundary markers or explicit instructions to ignore potentially malicious commands embedded in the fetched guidelines or user code.
  • Capability inventory: The skill is capable of reading local files provided by the user to perform design reviews.
  • Sanitization: The skill lacks specified sanitization or validation logic for content retrieved from external or local sources before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 12:19 PM