skill-system-tmux
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified. The skill is primarily instructional and provides a structured approach to using the standard tmux utility to prevent agent tool timeouts.\n- [COMMAND_EXECUTION]: The skill facilitates the execution of shell commands by routing them through detached tmux sessions. This is a core capability intended to support persistent background processes like dev servers or long-running builds.\n- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection because it processes arbitrary command strings as input.\n
- Ingestion points: Untrusted data enters via the 'command' and 'session_name' inputs in the skill manifest.\n
- Boundary markers: None; the skill acts as a pass-through layer for shell execution.\n
- Capability inventory: Ability to execute shell commands via tmux and terminate processes using kill.\n
- Sanitization: None; input validation is deferred to the agent's underlying shell tools.
Audit Metadata