brandkit
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
scripts/validate_tokens.py,scripts/validate_contrast.py,scripts/validate_theme_refs.py) and an NPM command (npm run verify) to validate generated design tokens. These are part of the internal verification workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied design briefs to generate token systems, which serves as an ingestion point for untrusted content.
- Ingestion points: User brief inference (Step 1).
- Boundary markers: None specified for the brief input.
- Capability inventory: Local script execution (
python3,npm) and file system writes (tokens/*.json,theme.css). - Sanitization: No sanitization of the input brief is described.
Audit Metadata