hypogenic

Warn

Audited by Snyk on Jun 27, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM context via the HypoRefine/Union literature path: PDFs placed by the user in literature/YOUR_TASK_NAME/raw/ are processed by pdf_preprocess.py/GROBID into readable text that is then used for literature-to-hypothesis prompting (i.e., third-party paper text not authored by the operating user).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 27, 2026, 11:42 AM
Issues
1
Security Audit — snyk — hypogenic