tokens
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill scans user-controlled project files such as CSS, JavaScript, and JSON for design tokens. This process creates an attack surface where malicious instructions could be embedded in those files. However, the skill implements a safe workflow by explicitly asking for user approval before writing any changes.
- Ingestion points: Project files like
tailwind.config.js,globals.css, anddesign-tokens.jsonare scanned for definitions in Step 1. - Boundary markers: The skill does not define specific delimiters to separate data from potential instructions within the scanned files.
- Capability inventory: The skill performs file system write operations after generating proposals in Steps 4 and 5.
- Sanitization: There is no mention of content sanitization or validation during the scanning process.
Audit Metadata