tmux

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides shell scripts and detailed instructions for executing tmux commands to manage interactive terminal sessions, send input, and scrape output history.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. 1. Ingestion points: Terminal output is captured via tmux capture-pane in SKILL.md, scripts/find-sessions.sh, and scripts/wait-for-text.sh. 2. Boundary markers: No explicit markers are used to distinguish terminal output from the agent's systemic instructions. 3. Capability inventory: The skill allows sending arbitrary keystrokes (tmux send-keys) and managing sessions (new-session, kill-session), which can be leveraged to execute commands. 4. Sanitization: Terminal data is captured and processed as raw text without validation or filtering for potential embedded commands or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM