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
tmuxandptylibraries. 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
tmuxand Pythonptyusage 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