literature-research

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to search and ingest content from open public sources (e.g., arXiv, Google Scholar, conference proceedings, technical blogs and industry reports) and to read/interpret paper abstracts/intros as part of its workflow, exposing it to untrusted third‑party content that could carry indirect prompt injection.