web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches guidelines from Vercel Labs' official GitHub repository. This is a well-known technology provider and the operation is consistent with the skill's purpose of auditing UI code compliance against established standards.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by retrieving and following rules from an external source.\n
  • Ingestion points: Guidelines are fetched via WebFetch from a remote repository in SKILL.md.\n
  • Boundary markers: No explicit markers are used to separate fetched rules from the agent's core instructions.\n
  • Capability inventory: The skill is limited to file reading (Read, Glob, Grep) and network fetching (WebFetch), and lacks permissions for command execution or file modification.\n
  • Sanitization: No content validation or sanitization is performed on the fetched guidelines before they are incorporated into the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 01:54 PM
Security Audit — agent-trust-hub — web-design-guidelines