analyze-ai-topics
Warn
Audited by Snyk on Oct 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The workflow queries and reads analytics data, metrics, and end-user conversation logs from Amplitude Agent Analytics via tools such as
search_agent_analytics_conversations, exposing the agent to untrusted user-submitted free text from chat interactions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata