auto-acl-apply

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to extract the Neptune x-jwt-token (or cookie) from browser network headers and then pass it verbatim as a --jwt parameter or include it in HTTP requests, which requires the LLM to handle and output secret values directly, creating an exfiltration risk.