ClawAudit verdict
mindsdb-mcp-skill
Legitimate MindsDB MCP integration for natural language database queries; uses the standard Agent+MCP architecture with no suspicious data routing or credential exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Findings (2)
Possible hardcoded credential
references/sdk-api.md · code · password='your-password
Python os.getenv — reads environment variable
README.md · code · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
network_in Is this flag fair?
Thanks — recorded.