auth-manager

Warn

Audited by Snyk on Feb 25, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The skill's config (~/.openclaw/auth-platforms.json) includes check_url/login_url entries and the auth_session_manager.py script uses Playwright to load and inspect those external web pages' DOM to decide session state and trigger alerts, so arbitrary public websites can directly influence the agent's decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 25, 2026, 08:30 AM