skills/sammii-hk/skills/design-system/Gen Agent Trust Hub

design-system

Pass

Audited by Gen Agent Trust Hub on Mar 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard Unix utilities like ls, cat, and grep to identify the project stack and analyze styles. These are legitimate operations for a design audit tool.
  • [EXTERNAL_DOWNLOADS]: Reference documentation suggests using npx contrast-ratio, which downloads a package from the npm registry, a well-known and trusted service.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it ingests content from project source files. * Ingestion points: cat and grep operations on user-controlled files like .css, .tsx, and .html. * Boundary markers: None; there are no instructions to the agent to isolate file content from its operation logic. * Capability inventory: Restricted to local file reading and basic text manipulation using standard CLI tools. * Sanitization: No input validation or escaping is applied to the analyzed code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 22, 2026, 10:18 PM