linkedin-post-research

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

• Third-party content exposure detected (high risk: 0.75). At runtime, the script calls Crustdata’s public endpoint to retrieve LinkedIn post objects and then ingests outsider-authored free text fields (e.g., post.get("text") into post_preview) into the produced JSON/CSV/summary, which can then be fed into an agent LLM context by downstream steps.