skills/jellydn/my-ai-tools/tmux/Gen Agent Trust Hub

tmux

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill's primary function is to execute shell commands via tmux to manage terminal sessions, send keystrokes, and capture output. This includes commands for session creation, key injection, and pane capture.
  • [EXTERNAL_DOWNLOADS]: The documentation recommends installing logpilot using cargo install logpilot. This tool is hosted on the author's GitHub repository and is presented as a utility for capturing and analyzing tmux output with AI.
  • [DATA_EXPOSURE]: The skill uses tmux capture-pane to read terminal output. While this is the intended functionality, users should be aware that the captured data is processed by the agent. The skill follows best practices by using isolated sockets in /tmp to prevent interference with the user's personal tmux sessions.
  • [INDIRECT_PROMPT_INJECTION]: As the skill is designed to capture and analyze terminal output from various processes (Python, GDB, etc.), it possesses an ingestion surface for untrusted data. If the processes running within tmux generate malicious output, it could potentially influence the agent's subsequent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 01:52 PM