deepsearch

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: LOWNO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists exclusively of markdown text. No Python scripts, Node.js packages, or shell commands are included.
  • DATA_EXFILTRATION (SAFE): The instructions involve reading local files for search purposes but do not include any network-related commands or external data transfer mechanisms.
  • PROMPT_INJECTION (SAFE): No instructions designed to override agent behavior or bypass safety filters were detected in the content or metadata.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 17, 2026, 11:48 AM