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.mdinto 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