list-building

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt instructs constructing shell/MCP calls that embed API keys and service-user credentials inline (e.g., BLITZAPI_KEY=..., MILLIONVERIFIER_API_KEY=..., and passing the literal service username into run_soql_query), which requires the LLM to include secret values verbatim in generated commands/requests — an exfiltration risk.