infographics

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

• Third-party content exposure detected (high risk: 0.90). The skill's AI pipeline (scripts/generate_infographic_ai.py — specifically research_topic and web_search which call the Perplexity Sonar Pro model via the OpenRouter API) fetches public web/search results and then _enhance_prompt_with_research injects that untrusted, third‑party content directly into the generation prompt, so the agent will read and act on external, user-generated/public web content.