marketing-pipeline-share-content-automation

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls ResearchService.search() (via POST /api/research and the pipeline’s research step) which “crawls real-time data” from outsider sources like TechCrunch/X/LinkedIn through RapidAPI, and that fetched outsider page/comment text is then JSON-stringified and injected into the LLM prompt in POST /api/generate as Research data: ${JSON.stringify(research)}.