tokens
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to scan for and read various project files, including CSS, JavaScript, and JSON configurations, to build a token inventory.\n- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection (Category 8).\n
- Ingestion points: The agent reads content from local project files like
tailwind.config.js,design-tokens.json, andglobals.css(SKILL.md, Step 1).\n - Boundary markers: Absent. The skill does not employ delimiters or ignore-instructions for the data ingested from local files.\n
- Capability inventory: The agent is empowered to suggest and write code changes to the filesystem (SKILL.md, Steps 4 and 5).\n
- Sanitization: Absent. The instructions do not specify validation or sanitization of the content found within project files before it is processed.
Audit Metadata