design-context

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is focused on design configuration and does not contain any instructions that attempt to bypass safety filters or exfiltrate data.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses local project files such as package.json, tailwind.config.js, and CSS files.
  • Evidence: Step 1 instructions specify scanning these files to extract design tokens (colors, fonts, etc.). This is a benign operation performed locally to automate design setup.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local project files, which represents a potential injection surface if the local environment is untrusted.
  • Ingestion points: Reads project files like package.json and tailwind.config.js in Step 1.
  • Boundary markers: Not explicitly defined in the instructions.
  • Capability inventory: File system read and write operations (.agents/design-context.md).
  • Sanitization: The skill logic focuses on extracting specific values (hex codes, font names) rather than executing instructions from the files, which mitigates the risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 07:36 PM
Security Audit — agent-trust-hub — design-context