web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [External Downloads] (LOW): The skill fetches remote content from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. While fetching remote instructions is a risk, this finding is downgraded to LOW per the [TRUST-SCOPE-RULE] as the repository belongs to a trusted organization (Vercel).
  • [Indirect Prompt Injection] (LOW): The skill possesses an attack surface for indirect prompt injection by fetching external data and using it as instructions for processing user files.
  • Ingestion points: Fetched content from the GitHub URL is treated as the rule set.
  • Boundary markers: Absent. The instructions do not specify delimiters to separate fetched guidelines from potentially malicious content within them.
  • Capability inventory: File reading, text output formatting.
  • Sanitization: None detected; the agent is instructed to directly apply all rules from the fetched guidelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 08:25 PM