baoyu-cover-image

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text from the user-supplied article.md / pasted “Direct content input” and then uses that text for content analysis and prompt creation (Step 1: Analyze Content; Step 3: Create Prompt), so an attacker can supply poison text directly via the required CLI input path.