drissionpage-mcp-browser-automation

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the drissionpage-mcp package from the Python Package Index (PyPI), which is a well-known service for Python dependencies.
  • [DYNAMIC_EXECUTION]: The skill provides the page_evaluate tool, enabling the execution of arbitrary JavaScript code within the context of the automated browser session.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection because it is designed to ingest data from external, untrusted websites.
  • Ingestion points: Data is pulled into the agent's context using tools like page_navigate, element_get_text, element_get_html, page_snapshot, and page_observe as defined in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following commands embedded in the scraped web content.
  • Capability inventory: The agent has access to sensitive capabilities such as page_evaluate, element_click, element_type, and element_upload_file (which uses DP_MCP_UPLOAD_ROOT as a security boundary) as listed in SKILL.md.
  • Sanitization: There is no evidence of automated sanitization or filtering for the external web data before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 10:45 PM
Security Audit — agent-trust-hub — drissionpage-mcp-browser-automation