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. Although this is a remote fetch, the organizationvercel-labsis explicitly listed as a Trusted GitHub Organization, resulting in a downgrade to LOW severity per [TRUST-SCOPE-RULE]. - [Indirect Prompt Injection] (LOW): The skill is designed to fetch instructions from an external URL and apply them to local files, creating a surface for potential injection if the remote source were compromised.
- Ingestion points: Remote markdown fetch defined in
SKILL.md. - Boundary markers: Absent. There are no explicit delimiters or instructions to ignore malicious content embedded in the fetched guidelines.
- Capability inventory:
WebFetch(network read) and local file system read access. - Sanitization: Absent. The agent is instructed to apply all rules from the fetched content directly to the user's code.
Audit Metadata