design-token-audit
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code and design files provided by the user, which could contain malicious instructions.
- Ingestion points: The 'Audit Process' in
SKILL.mdexplicitly instructs the agent to 'Extract all visual values from code/design files'. - Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the data being audited.
- Capability inventory: The skill itself does not contain scripts, network operations, or command execution patterns; it relies on the agent's base capabilities to read files.
- Sanitization: There are no instructions for sanitizing or validating the contents of the files before processing.
Audit Metadata