scan-design-system

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs legitimate project documentation tasks and restricts its operations to the local filesystem.
  • [COMMAND_EXECUTION]: Uses grep and glob for discovery of tokens and components within project directories, which is standard behavior for documentation tools.
  • [DATA_EXFILTRATION]: No network-capable commands or outbound data transfer patterns were detected.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted project data into documentation. 1. Ingestion: scans project source files and configuration JSON. 2. Boundary markers: absent. 3. Capability inventory: utilizes file system read/write and task management tools. 4. Sanitization: none present. The risk is considered minimal as findings are formatted as documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:25 AM