confluent-skill-creator
Warn
Audited by Snyk on Aug 13, 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). Runtime test scripts like
scripts/consume_and_verify.pysubscribe to a Kafka topic (specified via arguments from the user prompt/workflow) and ingest free-form message values from that topic into the LLM/verification context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata