publish-zsxq-article

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill instructs the agent to read a local Markdown file and embed its full content verbatim into a generated script/clipboard paste (const markdownContent = ...), which would force any secrets inside that file to appear in the agent's output—creating an exfiltration risk.