web-design-guidelines

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by design. It retrieves instructional rules from an external source and applies them to the user's files without safety boundaries.
  • Ingestion points: Guidelines are fetched from https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md into the agent's context.
  • Boundary markers: The skill does not use delimiters or instructions to ignore potential commands embedded in the external guidelines file.
  • Capability inventory: The skill possesses file-read capabilities to audit local UI code.
  • Sanitization: There is no validation or filtering of the content retrieved from the external URL before it is used to guide the agent's behavior.
  • [EXTERNAL_DOWNLOADS]: Fetches design guidelines from Vercel Labs' official GitHub repository to use as a rule set for the audit.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:02 AM