app-integrations

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the @useclawlink/cli package via npx. This is the official command-line interface for the ClawLink service, which manages the connections to the 90+ supported third-party applications.
  • [COMMAND_EXECUTION]: The skill defines a set of CLI commands for the agent to execute, including logging in, connecting to services, listing actions, and running specific tasks. These commands are necessary for the intended functionality of the integration hub.
  • [CREDENTIALS_UNSAFE]: The skill uses browser-based OAuth flows instead of requiring users to manually handle or hardcode API keys. While it notes that credentials are stored locally at ~/.clawlink/credentials.json, this is standard behavior for CLI tool session management and follows security best practices by avoiding plain-text secrets in the prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — app-integrations