tmux
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
tmuxbinary to manage terminal sessions, allowing for the execution of arbitrary shell commands within those sessions. - [PROMPT_INJECTION]: The skill provides mechanisms to read terminal output, which presents an indirect prompt injection surface if the scraped content contains malicious instructions.
- Ingestion points: Pane history is captured using
tmux capture-paneand thewait-for-text.shscript. - Boundary markers: There are no explicit delimiters or instructions to the agent to ignore content within the scraped terminal output.
- Capability inventory: The agent can interact with any shell process via
send-keysand has access to the local filesystem and network depending on the environment permissions. - Sanitization: No sanitization is performed on the output read from tmux panes before it is processed by the agent.
Audit Metadata