humanizer

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

• Third-party content exposure detected (high risk: 0.70). The skill’s runtime workflow is to “humanize” user-provided text by rewriting it, so any outsider-authored free text included in the input (e.g., pasted comments/issues/wiki text from others) would be ingested into the agent’s LLM context for editing.