skills/ampcode/amp-contrib/tmux/Gen Agent Trust Hub

tmux

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill uses the tmux binary for session management and sending keystrokes, which is standard and necessary for its intended purpose.
  • PROMPT_INJECTION (LOW): The skill exhibits an indirect prompt injection surface by design. 1. Ingestion points: Untrusted data enters the context via tmux capture-pane in SKILL.md. 2. Boundary markers: Absent; there are no instructions provided to wrap or delimit captured output to distinguish it from the agent's internal logic. 3. Capability inventory: The agent possesses powerful capabilities through tmux send-keys in SKILL.md, allowing it to execute arbitrary commands in the terminal. 4. Sanitization: Absent; the skill does not include or suggest any sanitization, filtering, or validation of the terminal output before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM