drissionpage-mcp-browser-automation

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides the page_evaluate tool which allows for the execution of arbitrary JavaScript within the browser context. This is a primary feature for web automation but represents a dynamic execution surface.- [EXTERNAL_DOWNLOADS]: The installation instructions guide users to download and install the drissionpage-mcp package from the official Python Package Index (PyPI).- [DATA_EXFILTRATION]: The skill includes tools to access potentially sensitive browser data. The browser_cookies_get tool can reveal cookie values when the show_value parameter is enabled, and the storage_get tool provides access to local and session storage content.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from external websites.
  • Ingestion points: SKILL.md (via navigation and extraction tools like page_snapshot, element_get_text, and page_console_logs).
  • Boundary markers: None explicitly defined in the instructions to separate web content from agent instructions.
  • Capability inventory: SKILL.md (includes JavaScript execution via page_evaluate, file uploads via element_upload_file, and navigation via page_navigate).
  • Sanitization: No specific sanitization or filtering of external web content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 04:38 AM
Security Audit — agent-trust-hub — drissionpage-mcp-browser-automation