google-bigquery

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @useclawlink/cli package from the public npm registry. This is a standard mechanism for utilizing the vendor's provided tooling.
  • [COMMAND_EXECUTION]: The instructions guide the agent to perform actions by executing shell commands. The skill explicitly advises the agent to confirm with the user before performing any write operations.
  • [CREDENTIALS_UNSAFE]: Authentication is handled via a browser login flow, and credentials (OAuth tokens) are stored locally at ~/.clawlink/credentials.json. This follows standard security practices for CLI-based tools to avoid hardcoding secrets in code or prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 02:42 PM
Security Audit — agent-trust-hub — google-bigquery