exploring-ai-failures
Warn
Audited by Snyk on Nov 2, 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 required workflow queries and reads PostHog LLM traces via
posthog:query-llm-traces-listandposthog:query-llm-trace, which ingest user-submitted production AI trace content (inputs, outputs, and messages from end-users).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata