vtuber-avatar-generation
Warn
Audited by Snyk on Feb 20, 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's SSE documentation (references/SSE-EVENTS.md) explicitly includes web_search_query and web_search_citations events that fetch and return external URLs from web searches (public sites), which the agent is shown using in example event flows and text responses—meaning untrusted third-party content can be ingested and influence the agent's subsequent actions.
Audit Metadata