screenshot-critique

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of instructions and a prompt template for visual critique. It does not involve any code execution, file system modifications, or network access.
  • [SAFE]: The workflow emphasizes security and isolation by explicitly setting fork_context: false when spawning sub-agents, which prevents the leakage of main thread history or implementation details to the secondary agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 01:50 PM
Security Audit — agent-trust-hub — screenshot-critique