skills/linkupplatform/openclaw/tmux/Gen Agent Trust Hub

tmux

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates arbitrary shell command execution and keystroke injection into tmux panes using the send-keys utility, providing broad control over terminal environments.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests unvalidated terminal output via tmux capture-pane. Malicious data displayed in a pane could potentially influence the agent's subsequent actions.\n
  • Ingestion points: Terminal output captured in SKILL.md and scripts/wait-for-text.sh.\n
  • Boundary markers: None; the raw terminal buffer is captured and processed without delimiters.\n
  • Capability inventory: Extensive shell access, file system interaction, and session management.\n
  • Sanitization: None; captured text is not filtered or sanitized before processing.\n- [DATA_EXFILTRATION]: The scripts/wait-for-text.sh script logs the entire captured pane history to stderr upon a timeout. This creates a risk of sensitive information disclosure if the terminal buffer contains credentials or private data when the timeout occurs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — tmux