hypogenic

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly clones and ingests public datasets from GitHub (e.g., HypoGeniC-datasets, Hypothesis-agent-datasets) and processes user-supplied literature PDFs in literature/YOUR_TASK_NAME/raw/ for hypothesis generation, so the agent reads and interprets untrusted third-party content as part of its workflow.