copywriting

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

• Third-party content exposure detected (high risk: 0.75). In the audit workflow, the user may supply a URL or pasted copy; the skill treats fetched/pasted text as data and then feeds that readable text into the LLM context for analysis (e.g., Step 2–5 scoring and report generation), which is outsider-authored free text.