immune

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly takes arbitrary input content, injects that full content into the scan request and then returns "the corrected content" (i.e., echoes/edits the input), so any API keys/passwords present in the input would be handled and output verbatim — creating an exfiltration risk.