research-expert
Warn
Audited by Snyk on Feb 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: 0.90). The skill explicitly instructs using WebSearch/fetching multiple pages ("Use WebSearch", "Fetch multiple pages simultaneously") and to capture/source content from the general web including blogs and forums ("General Web: Blogs, forums") and to include inline source URLs, so it ingests untrusted third‑party web content that could carry indirect prompt injection.
Audit Metadata