memory-lancedb-pro

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks users to paste API keys (or substitute them inline), instructs embedding those keys verbatim into curl commands and config blocks, and directs the agent to output/run Authorization headers with the secrets, which is direct insecure handling/exfiltration risk.