hypothesis-generation

Warn

Audited by Snyk on Apr 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly requires conducting literature searches via WebFetch on PubMed URLs and general WebSearch (papers, preprints, and other web content) that the agent is expected to read, synthesize, and use to drive hypotheses and experimental decisions, which exposes it to open third‑party web content that could carry indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 08:27 AM
Issues
1