firebase-vertex-ai
Warn
Audited by Snyk on Apr 4, 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 ingests untrusted user-generated content from Firestore (see ARD "Embedding + RAG Flow" and references/examples.md RAG and moderation examples) and includes that content directly in Gemini/Vertex AI prompts whose outputs drive responses and moderation actions, allowing indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata