docx-md

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill sends raw document text to the model and requires the model to output JSON fields like "originalContent" and "content" verbatim, so any secrets present in the document (API keys, passwords, tokens, cookies) would be reproduced in the model's output and could be exfiltrated.