tmux

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses tmux send-keys to interact with shell sessions, allowing for automated control of interactive command-line applications.
  • [PROMPT_INJECTION]: The script scripts/wait-for-text.sh reads terminal output, which is a potential surface for indirect prompt injection if the terminal contains data from untrusted sources.
  • Ingestion points: Terminal history and pane output captured via tmux capture-pane in scripts/wait-for-text.sh.
  • Boundary markers: None; output is captured directly from the tmux buffer without delimiters.
  • Capability inventory: Command execution and keystroke injection via tmux send-keys combined with output monitoring via tmux capture-pane.
  • Sanitization: None; raw terminal output is returned to the agent without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — tmux