error-analysis
Warn
Audited by Snyk on Nov 9, 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 pulls traces from the Langfuse API and ingests user-provided exported trace JSONL files containing production chat and agent interactions, which include outsider-authored free text from users interacting with the monitored system.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata