baoyu-danger-gemini-web

Warn

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/gemini-webapi/utils/load-browser-cookies.ts uses the child_process.spawn function to execute browser binaries (Chrome, Chromium, or Edge) with the --remote-debugging-port flag, allowing programmatic interaction with the browser process.
  • [DATA_EXFILTRATION]: The skill captures sensitive session cookies from the browser using a WebSocket connection to the Chrome DevTools Protocol. It specifically targets authentication tokens for Google domains, which are then stored in a local JSON file and used for subsequent network requests to Gemini endpoints.
  • [PROMPT_INJECTION]: The skill accepts external content through the --promptfiles and --reference parameters in scripts/main.ts. These ingestion points provide a surface for indirect prompt injection as the content is passed to the Gemini model without explicit sanitization or instruction delimiters. Capability inventory includes the ability to make authenticated API requests to Gemini services based on the processed inputs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 14, 2026, 03:59 PM
Security Audit — agent-trust-hub — baoyu-danger-gemini-web