end-to-end-orchestrator
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 Research stage explicitly invokes multi-ai-research (e.g., "Gemini research: Web best practices, latest trends" and "Codex research: GitHub patterns, code examples") and writes research findings with citations, which indicates the agent fetches and ingests public web/GitHub content that could contain untrusted, user-generated material.
Audit Metadata