login-microsoft-sso

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the chrome-cdp CLI tool to interact with the user's browser. It executes shell commands to retrieve the browser endpoint and start the debugging daemon.
  • [DATA_EXPOSURE]: The skill reads application-specific configurations (URLs and button names) from a local configuration file located at ~/.config/harness-configs/login-microsoft-sso/config. This is a standard practice for managing environment-specific settings.
  • [SAFE]: The skill implements strong security principles by explicitly stating it does not handle or type user credentials, relying instead on the user's existing active session and hardware-based authentication (passkeys).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 08:53 AM
Security Audit — agent-trust-hub — login-microsoft-sso