system
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external source code and documentation files to perform UI consistency audits, creating a potential surface for indirect prompt injection.\n
- Ingestion points: Locates and reads token, primitive, feature-component, layout, and documentation sources (e.g.,
src/styles/globals.css,src/components/ui/,DESIGN.md).\n - Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions embedded within the processed data.\n
- Capability inventory: The skill is scoped to analysis, reporting, and documentation updates. It does not require or utilize network access, shell command execution, or other high-privilege operations.\n
- Sanitization: No sanitization or validation of the ingested file content is specified.\n- [SAFE]: No malicious patterns such as remote code execution, credential harvesting, or obfuscation were detected in the skill instructions or metadata.
Audit Metadata