design-tokens
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill's instructions or code examples.
- [PROMPT_INJECTION]: The skill involves reading and processing project source code, which constitutes an indirect prompt injection surface.
- Ingestion points: Source files (.css, .tsx) are accessed via Glob, Grep, and Read tools as defined in SKILL.md.
- Boundary markers: No specific delimiters or instructions are defined to isolate untrusted code content from agent instructions.
- Capability inventory: The agent has permissions to modify files (Write, Edit) and execute specific shell commands (Bash).
- Sanitization: Code content is not explicitly sanitized before processing.
- [COMMAND_EXECUTION]: The skill recommends several utility commands using grep, find, and npx stylelint for project auditing and linting. These are standard development tools and their use is restricted to appropriate file types and directories.
Audit Metadata