earn-hunter

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user for a Lark webhook URL and "write to platform.notify.lark_webhook" (i.e., accept and store a secret supplied in chat verbatim), which forces the LLM to handle secret values directly and creates an exfiltration risk.