Deal Next Best Actions

Warn

Audited by Snyk on Mar 3, 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.md explicitly requires Layer 2 "Enrichment (Web Search)" to search public web content (e.g., "{company_name} news") and map external trigger events to specific actions, so the agent fetches and interprets untrusted third‑party web content that can materially change its recommended next steps.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 11:37 AM