gsp-project-brief

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes project-specific data like BRIEF.md and config.json, which introduces an indirect prompt injection surface.
  • Ingestion points: BRIEF.md, config.json.
  • Boundary markers: None.
  • Capability inventory: Read, Write, Bash, Grep, Glob.
  • Sanitization: None.
  • [COMMAND_EXECUTION]: The Bash tool is utilized for project structure navigation and path resolution tasks within the design system directory.
  • [SAFE]: The skill does not perform external network requests, use obfuscation, or attempt persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 04:01 AM