tooluniverse-epigenomics

Warn

Audited by Snyk on Apr 16, 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 and REFERENCE.md explicitly call ToolUniverse tools to fetch and parse public third‑party annotations and experiment data (e.g., Ensembl, SCREEN, ChIPAtlas, ENCODE, JASPAR, ReMap, RegulomeDB) and then use those results to annotate data and drive analysis decisions, which exposes the agent to untrusted external content that could materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 16, 2026, 08:28 AM
Issues
1