gui-control

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documentation and provided commands do not contain any malicious patterns, obfuscation, or unauthorized access attempts. The architecture relies on a local binary and Unix socket for secure IPC.
  • [COMMAND_EXECUTION]: The skill utilizes the autopcb-shell binary to perform GUI actions and PCB-related tasks. These commands are localized to the application's functionality and do not involve privilege escalation or unsafe shell practices.
  • [SAFE]: Analysis of the attack surface for indirect prompt injection reveals that while the skill processes visual data (screenshots), it lacks dangerous automated capabilities that would make such an injection exploitable.
  • Ingestion points: Screenshots captured via autopcb-shell screenshot and CLI responses.
  • Boundary markers: Not explicitly defined in the CLI communication.
  • Capability inventory: Local GUI control and file management; no network or administrative capabilities.
  • Sanitization: None required for the current scope of tool interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 05:37 AM
Security Audit — agent-trust-hub — gui-control