infographics

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

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow ingests outsider-authored free text from the user-provided infographic PROMPT into scripts/generate_infographic_ai.py where it is sent to Gemini for image generation and review, and it may also be used as the research query for Perplexity Sonar when --research is enabled.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The generator calls the OpenRouter API at https://openrouter.ai/api/v1 at runtime (see base_url in scripts/generate_infographic_ai.py) and the returned Perplexity Sonar research content is injected into subsequent generation prompts, so external content directly influences prompts.