browser-mcp-control

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches source code from a GitHub repository and recommends downloading a Chrome extension from the vendor's website.
  • [COMMAND_EXECUTION]: Requires the user to run shell commands for installation and build processes, and configures the AI client to execute a local Node.js subprocess.
  • [PROMPT_INJECTION]: Susceptible to indirect prompt injection where malicious instructions embedded in web pages could influence agent behavior.
  • Ingestion points: Tools such as browser_snapshot and browser_get_console_logs in SKILL.md read untrusted content from the web.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation.
  • Capability inventory: Includes browser navigation, element interaction (clicking, typing, hovering), and keyboard input execution.
  • Sanitization: No sanitization or validation of the ingested web content is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 03:09 AM
Security Audit — agent-trust-hub — browser-mcp-control