anti-detect-browser

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as clear instruction and reference material for an automation SDK. No executable scripts, binaries, or dynamic execution paths are provided within the skill payload.
  • [SAFE]: The external services, registry targets (anti-detect-browser on npm, antibrow on PyPI), and API hosts (https://antibrow.com) align consistently with the vendor identity ('antibrow') and present no risks of typosquatting or brand impersonation.
  • [SAFE]: The skill follows security best practices by explicitly instructing the agent and operator to read credentials and proxy authentication details directly from the host environment rather than hardcoding them.
  • [SAFE]: The documentation includes an architecture and design advisory on handling third-party page content safely (treating DOM output as untrusted input), mitigating risks of indirect prompt injections.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:04 AM
Security Audit — agent-trust-hub — anti-detect-browser