web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Feb 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill fetches a remote markdown file (
command.md) which contains the logic and rules for the agent to follow. - Evidence: Source URL
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.md. - Trust Status: The organization
vercel-labsis a trusted source, downgrading the severity of this external dependency per security policy. - [PROMPT_INJECTION] (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it processes untrusted local files.
- Ingestion points: Reads local files or file patterns provided by the user in
SKILL.md. - Boundary markers: None specified in the instructions to prevent the agent from obeying instructions embedded within the analyzed UI code.
- Capability inventory: File reading and remote fetching via
WebFetch. - Sanitization: No sanitization or validation of the input file content is mentioned.
Audit Metadata