ocr

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [SAFE] (SAFE): No malicious patterns detected. The skill performs intended OCR functions using local tools.
  • [INDIRECT_PROMPT_INJECTION] (INFO): The skill processes untrusted text extracted from images. While it lacks sanitization or boundary markers, the impact is limited to the system clipboard, which does not constitute an execution or exfiltration risk. * Ingestion points: Local image files (SKILL.md) * Boundary markers: Absent * Capability inventory: System clipboard write access (scripts/copy_to_clipboard.sh) * Sanitization: Absent
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 10:41 AM