triage
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is designed to provide recommendations based on a quick assessment of a design system's state. Its primary function is to generate a text-based prioritized plan for other skills.
- [SAFE]: No network operations, credential harvesting patterns, or persistence mechanisms were detected in the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill scans untrusted codebase environments for specific file patterns and directory counts to classify system maturity. This ingestion of external data is considered safe because the skill has no dangerous capabilities (no file writes, network requests, or command execution) and its output is strictly limited to generating a markdown report.
- Ingestion points: Scans codebase directories and file names for tokens and documentation (SKILL.md, Step 1).
- Boundary markers: None identified.
- Capability inventory: The skill performs text generation only; no code execution, network access, or system modifications are included.
- Sanitization: No specific sanitization logic is present, but none is required for the skill's current scope of producing text recommendations.
Audit Metadata