tmux
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Command Execution] (SAFE): The scripts
find-sessions.shandwait-for-text.share well-structured bash scripts that use safe command-line parsing and properly handle variables to avoid shell injection vulnerabilities.\n- [Indirect Prompt Injection] (LOW): The skill enables an attack surface for indirect prompt injection because the agent processes output from potentially untrusted terminal sessions.\n - Ingestion points: Terminal content is ingested via
tmux capture-panecommands inSKILL.mdand thewait-for-text.shscript.\n - Boundary markers: Absent. The instructions do not provide the agent with mechanisms to distinguish between its own instructions and data read from the terminal pane.\n
- Capability inventory: The agent possesses powerful capabilities, specifically the ability to execute arbitrary commands in the terminal using
tmux send-keys.\n - Sanitization: Absent. The skill captures and processes terminal output as raw text without any sanitization or validation logic.
Audit Metadata