linkedin-content

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

• Third-party content exposure detected (low risk: 0.10). In the required runtime workflow, outsider-authored free text is ingested only via the caller-provided LinkedIn post “material”/draft (e.g., repurpose_splitter.py --input …, post_linter.py --input/--text reading local files or stdin), and there is no built-in queue/feed browsing or arbitrary external text fetching.