design-tokens
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (
contrast.py,validate_tokens.py) and utilizes standard shell commands (ls) to perform accessibility audits and validate the integrity of design tokens. These actions are limited to the local filesystem relative to the project environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from external project files, creating a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion Points: Reads markdown rules from
.claude/rules/and JSON token definitions from thetokens/directory. - Capability Inventory: The skill is capable of executing local shell commands and Python scripts.
- Boundary Markers: The instructions lack specific delimiters or markers to differentiate between the agent's instructions and the data being read from files.
- Sanitization: No explicit sanitization or instruction filtering is applied to the content of the ingested markdown or JSON files before processing.
Audit Metadata