hypothesis-generation

Warn

Audited by Snyk on Apr 11, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly requires conducting web literature searches and using WebFetch/WebSearch to retrieve PubMed pages, preprints, and other web sources ("Use WebFetch with PubMed URLs" and "Use WebSearch to find recent papers, preprints, and reviews"), so the agent will fetch and interpret open/public third‑party content that can influence its hypotheses and actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 11, 2026, 10:27 PM
Issues
1