skill-optimizer-lawvable

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to quote user conversation verbatim (e.g., "exact instruction to add", "Source: [quote from conversation]", and AskUserQuestion) and to write those quotes into outputs and files, so any API keys or secrets present in the conversation would be emitted verbatim and exposed.