humanizer

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s required workflow ingests outsider-authored free text directly from the user (“Accept the text to humanize as: a pasted block, a file path (use Read), or the current selection”) and then loads the vendored rulesets to process that user content, so it is exposed to arbitrary free text at Step 1/Step 5.