vercel-skills
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches web design and writing guidelines from official Vercel Labs repositories on GitHub (
vercel-labs/web-interface-guidelinesandvercel-labs/writing-guidelines) during the review process. - [COMMAND_EXECUTION]: The skill provides instructions and commands to install a suite of specialized agent skills using
npx skills add, targeting the officialvercel-labs/agent-skillsrepository. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill is designed to fetch external rule sets from GitHub repositories (documented in
SKILL.md) to guide its review process. - Boundary markers: None explicitly defined in the provided stub files.
- Capability inventory: The stub itself does not contain executable scripts, but the described skills involve reviewing code and prose against the fetched guidelines.
- Sanitization: No specific sanitization or filtering logic is documented for the external guidelines fetched at runtime.
Audit Metadata