baoyu-article-illustrator

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

• Third-party content exposure detected (medium risk: 0.65). The skill ingests outsider-authored free text when the operating user provides pasted article content (Step 1.1 “Pasted content” → Step 2 “Analyze content” → Step 5 “LABELS: use actual numbers/terms/quotes from the article”), and that pasted content is not authored by the operating user, so it can be fed into the agent’s LLM context for analysis/prompt construction.