accelerating-pipeline
Warn
Audited by Snyk on Feb 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The workflow (workflow.md — Phase 3 “Signal-Based Engagement System” and the AI Agent Architecture) explicitly instructs a Signal Collection Agent to ingest signals from third-party intent providers and social/review platforms (e.g., Bombora, G2, TrustRadius, LinkedIn, review sites), and those external, user-generated signals are used by scoring, routing, and personalization agents to drive immediate actions, so untrusted third‑party content can materially alter agent behavior.
Audit Metadata