vulnerability-discovery
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's Attack Surface Analysis explicitly lists "Indirect Input" including "Web content (browsing/scraping)" and "RAG context (retrieved documents)" — indicating the agent is expected to ingest untrusted public web/third-party content as part of its workflow, which could enable indirect prompt injection.
Audit Metadata