vs-search-tuning-specify-policy-direction

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly tells the agent that "if the user has already provided AK/SK, pass --ak/--sk / env explicitly", which would require the LLM to emit secrets verbatim in commands or environment usage, creating an exfiltration risk.