x-product-deep-research

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests open/public web content via the "Deep Research" phase and then extracts and downloads YouTube video URLs from the deep research report ("Video Resources" section) for analysis (Phase 1–3 in SKILL.md), so untrusted, user-generated third‑party content is read and used to drive tool actions and decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 04:13 AM