infographics

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

• Third-party content exposure detected (medium risk: 0.30). In scripts/generate_infographic_ai.py, when the user enables --research, the workflow calls research_topic() using Perplexity Sonar (requests.post to https://openrouter.ai/api/v1/chat/completions) and ingests the resulting untrusted free-text content into the generation prompt via _enhance_prompt_with_research().