event-streaming
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: A comprehensive audit of the skill found no evidence of prompt injection, obfuscation, or malicious code. The skill correctly recommends using environment variables for credentials and focuses on standard data engineering tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates ingestion of untrusted data from external sources like Kafka topics and data warehouses. Ingestion points are located in SKILL.md and throughout the references/ folder. The skill's capability inventory includes generating data processing logic. Sanitization is addressed via recommendations for Schema Registry integration, Dead Letter Queues (DLQ), and PII masking as documented in references/kafka-deep-dive.md. Boundary markers are recommended through strict schema enforcement principles.
Audit Metadata