exploring-llm-traces
Warn
Audited by Snyk on Nov 5, 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 inspects PostHog AI trace logs and LLM session histories, which store runtime prompt inputs, user messages, and model responses containing arbitrary external text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata