design-agentic-architecture
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). Step 7 (“Recommend tools — live”) requires fetching/searching current web content at runtime, which can ingest outsider-authored free text (public pages/results) into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata