kogiqa-mcp-browser-automation

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the kogiqa-mcp server package from the official npm registry via npx.
  • [REMOTE_CODE_EXECUTION]: Installation instructions utilize npx kogiqa-mcp@latest, which downloads and executes the server-side logic locally to enable browser automation capabilities.
  • [PROMPT_INJECTION]: The kogiqa_get_content tool retrieves raw HTML or text from external websites, creating a surface for indirect prompt injection where malicious instructions on a webpage could attempt to influence the agent's behavior.
  • Ingestion points: kogiqa_get_content (SKILL.md)
  • Boundary markers: Absent
  • Capability inventory: kogiqa_navigate, kogiqa_click, kogiqa_type, kogiqa_get_content, kogiqa_screenshot, kogiqa_close (SKILL.md)
  • Sanitization: Not specified for retrieved content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:20 AM
Security Audit — agent-trust-hub — kogiqa-mcp-browser-automation