hypogenic

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests open/public third-party content—e.g., cloning public dataset repos (https://github.com/ChicagoHAI/HypoGeniC-datasets.git), processing user-supplied literature PDFs in literature/... via GROBID, and examples mentioning social media posts—and the agent is expected to read and interpret those data/papers as part of hypothesis generation, exposing it to untrusted user-generated content that could enable indirect prompt injection.