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 content from 'https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md' to determine its rules and behavior. While this is an external dependency, the 'vercel-labs' organization is a trusted source, allowing for a severity downgrade per [TRUST-SCOPE-RULE].
- PROMPT_INJECTION (LOW): This skill is vulnerable to Indirect Prompt Injection (Category 8) because it treats remote data as executable instructions for the agent.
- Ingestion points: The 'command.md' file fetched via WebFetch in 'SKILL.md'.
- Boundary markers: Absent; the instructions tell the agent to 'apply all rules from the fetched guidelines' without explicit delimiters for the external content.
- Capability inventory: The skill has the capability to read local files provided by the user.
- Sanitization: Absent; there is no validation of the remote content before it is adopted as agent instructions.
Audit Metadata