m-tokens
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill performs analysis on the local codebase to generate design tokens. This creates a surface where instructions hidden within source code files (such as in comments or variable names) could potentially influence agent behavior.
- Ingestion points: Processes codebase files to extract colors, typography, and spacing values.
- Boundary markers: No specific delimiters or instructions to disregard embedded commands in the source files are present.
- Capability inventory: No executable scripts or tool-calling capabilities are defined within this skill.
- Sanitization: No sanitization or filtering of the ingested code content is mentioned.
Audit Metadata