mcp-server

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes explicit examples and flows that embed OAuth client_secrets and bearer tokens directly into HTTP headers/requests and configuration files (e.g., curl -H "Authorization: Bearer [token]" and client_secret=[secret]), which encourages the LLM to output secret values verbatim if populated and thus creates exfiltration risk.