browserstack

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development commands such as npx playwright test to run testing suites and npm install for the browserstack-local package. These operations are aligned with the skill's stated purpose and use common development tools.
  • [DATA_EXFILTRATION]: The skill utilizes BROWSERSTACK_USERNAME and BROWSERSTACK_ACCESS_KEY environment variables to authenticate with BrowserStack's official WebSocket endpoint (wss://cdp.browserstack.com). This is a standard and expected operation for this well-known service.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the browserstack-local package and references official BrowserStack documentation and dashboard URLs. These are well-known resources for cross-browser testing and are used as intended for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes test logs and build results via MCP tools. While this represents an ingestion surface for external data, the risk is minimal given the context of automated testing outputs from a well-known service.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 08:16 AM
Security Audit — agent-trust-hub — browserstack