dispute

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs the orchestrator to read "relevant files" and send "FULL context" (including files and prior decisions) to external models and to record results, which would cause any embedded secrets or API keys to be included verbatim in messages and saved outputs, creating exfiltration risk.