Skills
skills/smallnest/goclaw/tmux/Gen Agent Trust Hub

tmux

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides scripts and instructions to send arbitrary keystrokes and shell commands to tmux terminal panes.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by capturing and acting upon data from terminal sessions. • Ingestion points: The scripts/wait-for-text.sh script captures terminal pane history via tmux capture-pane for pattern matching. • Capability inventory: The agent uses tmux send-keys throughout the skill to execute commands and provide input to processes. • Boundary markers: Terminal output is not isolated or wrapped in delimiters, increasing the risk of the agent interpreting data as instructions. • Sanitization: The skill does not sanitize terminal output before processing it, allowing malicious text within a session to potentially influence agent behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 10:38 PM