pmg-image-decomposer

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill provides documentation and API usage examples for image decomposition and PowerPoint integration.
  • [DATA_EXFILTRATION]: No network operations or unauthorized data transfer patterns are present; the skill performs local file operations for image decomposition.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted image data through the source_path parameter. While this represents an attack surface, the decomposition logic (semantic, geometric, and depth) is based on computer vision principles rather than natural language interpretation, significantly reducing the risk of instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 08:03 PM