skill-scanner

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Data Exposure & Exfiltration (SAFE): The script reads metadata from local skill files; it does not access sensitive data or perform network exfiltration.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): No external dependencies are used. The script contains no dynamic code execution functions.
  • Command Execution (SAFE): The script does not execute shell commands or subprocesses.
  • Network Operations (SAFE): The skill lacks networking code.
  • Indirect Prompt Injection (SAFE): The tool has no exploitable capabilities (write/exec) to act on data read from scanned files. Evidence Chain: (1) Ingestion: scripts/scan_skills.py. (2) Boundaries: None. (3) Capability: Read-only. (4) Sanitization: Truncates output.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:48 PM