tmux
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands within tmux sessions using the
send-keyscommand for process management. - [INDIRECT_PROMPT_INJECTION]: The skill includes patterns for monitoring process output using
tmux capture-pane, which introduces a surface for indirect prompt injection if the monitored process outputs malicious instructions. - Ingestion points: Process output captured via
tmux capture-paneinSKILL.md. - Boundary markers: None present.
- Capability inventory: Execution of shell commands via
tmuxand other local utilities inSKILL.md. - Sanitization: No sanitization or validation of the captured terminal output is described.
Audit Metadata