web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' public GitHub repository. This operation is consistent with the skill's stated purpose of providing UI audits.
  • [PROMPT_INJECTION]: Indirect Prompt Injection Risk.
  • Ingestion points: Fetches instructions and rules from an external URL (https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md) which the agent is instructed to follow.
  • Boundary markers: The skill does not define delimiters or specific "ignore" instructions to isolate the fetched rules from the agent's core instructions.
  • Capability inventory: The agent reads local files and formats output based on instructions retrieved from the external source.
  • Sanitization: No validation or sanitization is performed on the fetched content before the agent processes it as instructions.
  • [PROMPT_INJECTION]: Metadata Inconsistency. The internal metadata specifies 'vercel' as the author, which does not match the skill's actual publisher 'lotfb86'. This deceptive labeling could lead to incorrect assumptions about the skill's origin.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:17 AM
Security Audit — agent-trust-hub — web-design-guidelines