matrixscan-batch-kmp

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill prompt explicitly instructs the agent to retrieve a secret API key via MCP (get_license_key) and then write it directly into the source code ("write it into the licence-key call in place of the placeholder"), creating a high risk of exfiltrating credentials through the LLM's context and output.