tmux-agent
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill grants the agent the ability to execute shell commands using 'tmux send-keys'. This is the core functionality and is used as intended for orchestration.
- [PROMPT_INJECTION] (LOW): Potential surface for indirect prompt injection (Category 8).
- Ingestion points: Data from external processes is captured via 'tmux capture-pane' (found in SKILL.md and 01-capture-patterns.md).
- Boundary markers: Absent; no delimiters are defined to separate captured text from agent instructions.
- Capability inventory: Full terminal access is available via 'tmux send-keys' (referenced in SKILL.md and 02-send-keys-safety.md).
- Sanitization: No sanitization is performed on ingested terminal output to mitigate malicious instruction following.
Audit Metadata