datarobot

Warn

Audited by Snyk on Mar 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: 0.70). The skill explicitly includes a "Create Dataset from URL" action in SKILL.md that imports data from an arbitrary remote URL (untrusted third-party content) which the agent would ingest and could materially influence subsequent analyses or actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 16, 2026, 03:02 AM
Issues
1