web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines from a public repository hosted by Vercel Labs on GitHub.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it retrieves runtime instructions from an external URL to determine its behavior.
- Evidence Chain for Indirect Prompt Injection:
- Ingestion points: Remote markdown content is fetched from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdinSKILL.md. - Boundary markers: None identified; the skill does not wrap the external content in protective delimiters.
- Capability inventory: The skill is authorized to read local files and generate reports based on the external rules.
- Sanitization: No sanitization or validation of the fetched instructions is performed before they are integrated into the agent's reasoning process.
Audit Metadata