polish-japanese-docs

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires returning the full rewritten document and explicitly forbids altering code blocks/command examples, so any secrets present in the input (API keys, tokens, passwords) would be reproduced verbatim in the output, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). SKILL.md defines a rewrite/polish workflow that reads the user-provided “Target text” (inline text or a referenced file path) end-to-end before rewriting, so outsider-authored free text is directly ingested at runtime.