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 fetches guidelines from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md'. While this involves downloading remote instructions, the source 'vercel-labs' is a trusted GitHub organization, resulting in a downgraded severity level per the [TRUST-SCOPE-RULE].
- PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes user-provided files that could contain malicious instructions designed to subvert the audit process. Evidence chain: 1. Ingestion points: User-specified files or patterns read during the review process. 2. Boundary markers: Absent; no explicit delimiters or warnings for the agent to ignore instructions within the target files are specified. 3. Capability inventory: File reading and network fetching (WebFetch). 4. Sanitization: Absent; the skill lacks mechanisms to sanitize or validate the content of the files before processing.
Audit Metadata