debug-bridge

Fail

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill implements js and eval commands that enable the execution of arbitrary JavaScript code within the connected browser session.
  • [DATA_EXFILTRATION]: The tool facilitates the capture of sensitive information, including browser cookies, localStorage data, and full network request/response bodies which may contain session tokens or personal information.
  • [EXTERNAL_DOWNLOADS]: The documentation instructs the user to install the debug-bridge-browser package and execute npx debug-bridge-cli, which involves downloading and running code from the npm registry at runtime.
  • [COMMAND_EXECUTION]: The skill uses tmux to manage a persistent CLI server and executes various shell commands (e.g., npx, tmux send-keys, open) to control the debugging environment.
  • [PROMPT_INJECTION]: By reading and processing data from external web applications—such as UI trees, console logs, and network traffic—the skill is exposed to indirect prompt injection where malicious web content could attempt to manipulate the agent's instructions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 25, 2026, 03:13 PM
Security Audit — agent-trust-hub — debug-bridge