mcp-setup

Fail

Audited by Snyk on Feb 16, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the setup to prompt for the Voyage AI API key and to generate/update .mcp.json with an env entry (VOYAGE_API_KEY) which would require the agent to capture and embed the secret verbatim into the config file.
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 02:23 AM