web-design-guidelines
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches design guidelines and audit rules from a repository under the vercel-labs GitHub organization.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by dynamically loading instructions from an external source.\n
- Ingestion points: Rules and formatting instructions are retrieved from
https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/main/command.mdat runtime within theSKILL.mdlogic.\n - Boundary markers: There are no delimiters or explicit instructions provided to the agent to treat the fetched content as data rather than instructions, nor are there warnings to ignore embedded overrides.\n
- Capability inventory: The agent has permissions to read local files specified by the user or identified via patterns to perform the design review.\n
- Sanitization: The fetched content is applied directly to the agent's context without any validation, filtering, or schema enforcement.
Audit Metadata