workorai

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill uses a dedicated Node.js script (scripts/credential-store.mjs) to manage WorkorAI API keys securely. It prioritizes system-level secret storage such as macOS Keychain, Linux Secret Service, and Windows SecretManagement over local file storage.
  • [SAFE]: For local file storage of credentials, the skill enforces strict file permissions (0600) and uses a shared configuration directory (~/.config/workorai/), which is a standard and secure practice for CLI-based tooling.
  • [SAFE]: The instructions and the management script include explicit logic to redact WorkorAI API keys (following the wai_... pattern) in any output visible to the user, preventing accidental credential exposure in chat transcripts.
  • [COMMAND_EXECUTION]: The provided management script invokes local system binaries like security, secret-tool, and powershell to perform credential operations. These calls are implemented using execFileSync and spawnSync with validated parameters, mitigating the risk of command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 01:25 AM
Security Audit — agent-trust-hub — workorai