tui-tester

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Terminal Automation and Command Execution: The skill provides instructions for the agent to manage a testing daemon and interactive terminal sessions using tmux and a specialized automation tool (agent-tui). This includes starting/stopping background processes and managing temporary files in /tmp to ensure a consistent environment for visual validation. These operations are standard for terminal automation tasks.
  • Environment Configuration: The skill sets specific environment variables such as GEMINI_CLI_TRUST_WORKSPACE=true to streamline the testing process by bypassing interactive modals. This is a common practice in automated testing workflows to avoid blocking the automation script on security or configuration prompts.
  • Indirect Prompt Injection Surface: The testing workflow involves a loop where the agent waits for specific strings in the terminal output before proceeding. Because the agent's logic is driven by external data (terminal output from the application being tested), this represents a potential surface where untrusted output could influence subsequent agent actions. This is an inherent consideration for any skill that automates interactive applications.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:27 AM
Security Audit — agent-trust-hub — tui-tester