web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS] (LOW): The skill is configured to fetch guidelines and instruction logic from a remote GitHub repository.
  • Evidence: Fetching from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md.
  • Trusted Source: The repository belongs to the vercel-labs organization, which is a trusted entity, downgrading the severity from MEDIUM/HIGH to LOW per security protocols.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) due to its core functionality.
  • Ingestion points: Remote URL instructions (command.md) and user-provided local source code files.
  • Boundary markers: No explicit delimiters or 'ignore instructions' wrappers are defined to separate code from data during processing.
  • Capability inventory: The agent has the capability to read local filesystem contents and perform network fetches.
  • Sanitization: No sanitization or validation of the fetched markdown content or local files is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:47 PM