baoyu-danger-gemini-web

Fail

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill performs automated extraction of sensitive session cookies (__Secure-1PSID and __Secure-1PSIDTS) from the user's web browser. This is implemented in scripts/gemini-webapi/utils/load-browser-cookies.ts using the Chrome DevTools Protocol (CDP).
  • [COMMAND_EXECUTION]: The skill launches browser processes (Chrome, Edge, etc.) via child_process.spawn to facilitate the extraction of session cookies. The executable path can be influenced by the GEMINI_WEB_CHROME_PATH environment variable.
  • [DATA_EXFILTRATION]: Sensitive Google authentication cookies are scraped from the browser and stored in a local JSON file at a path such as ~/Library/Application Support/baoyu-skills/gemini-web/cookies.json (on macOS) or similar paths on other platforms. This exposes the user's persistent Google session to the local filesystem in an unencrypted format.
  • [EXTERNAL_DOWNLOADS]: The skill downloads generated images and web content from Google's domains (google.com, googleusercontent.com) and uploads local files for vision-based processing to content-push.googleapis.com.
  • [PROMPT_INJECTION]: As a tool that processes arbitrary user input and interpolates it into network requests to an external LLM, it is susceptible to indirect prompt injection if the processed data (e.g., contents of --promptfiles) contains malicious instructions designed to influence the agent's next steps.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jun 28, 2026, 03:19 AM
Security Audit — agent-trust-hub — baoyu-danger-gemini-web