ai-news-bitable-archive

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The entrypoint example requires passing a Feishu "base token" (and potentially doc token) as a command-line argument, which instructs the agent to embed secret API tokens verbatim in generated commands—an explicit high-risk exfiltration pattern.