control-cli

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to manage terminal sessions via tmux and pty libraries. These are standard procedures for the skill's primary purpose of CLI/TUI testing and profiling.- [SAFE]: The skill includes explicit security guardrails in the 'Guardrails' section, directing the agent not to send credentials or destructive commands into sessions and to clean up all temporary artifacts.
  • [SAFE]: Code examples for tmux and Python pty usage are standard templates for terminal automation and do not contain malicious payloads or obfuscation.
  • [SAFE]: Network operations mentioned (e.g., --inspect=127.0.0.1:0) are restricted to the local loopback interface for debugging purposes and do not facilitate external data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:52 AM
Security Audit — agent-trust-hub — control-cli