visual-design
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary function is to analyze CSS properties (box-shadow, border-radius, padding) against a set of hardcoded design guidelines. It does not request or use any network, shell, or administrative tools.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by reading CSS files from the user's project.
- Ingestion points: CSS files in the project scope.
- Boundary markers: None specified for the input data.
- Capability inventory: The skill is limited to reading files and outputting text reports; it lacks capabilities for network access, file writing, or command execution.
- Sanitization: Not explicitly implemented, but the lack of dangerous capabilities mitigates the risk.
Audit Metadata