couchbase-mcp

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions for interacting with Couchbase through clearly defined tool families (cb_, admin_, capella_*). It demonstrates a strong security posture by including a dedicated safety reference (references/safety.md) that explains confirmation gates and read-only modes.
  • [SAFE]: All external references, such as the Capella API endpoint (cloudapi.cloud.couchbase.com) and the project's GitHub repository, belong to trusted or well-known service domains related to the skill's primary purpose.
  • [SAFE]: Operational runbooks for high-stakes tasks like cluster upgrades and data restoration include explicit warnings and recommend non-destructive verification steps (e.g., restoring to a temporary bucket first).
  • [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found in any of the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:29 PM
Security Audit — agent-trust-hub — couchbase-mcp