kafka-schema-registry
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a specialized scanner for Kafka producers and consumers. It uses standard tools (Glob, Grep, Read, Write) to analyze project source code and generate infrastructure-as-code (Terraform) and analysis reports. All external resources, such as the Confluent Terraform provider and Schema Registry packages, are official vendor-owned resources that align with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted source code from external projects to infer schemas.
- Ingestion points: Project source files (Java, Python, C#, Go, Node.js) identified during the scan phase.
- Boundary markers: The instructions do not specify the use of delimiters when processing code content.
- Capability inventory: The skill uses Read, Write, Glob, and Grep tools. It does not perform network operations or execute the code it analyzes.
- Sanitization: The skill extracts field names and types from code to generate schema files and Terraform; explicit sanitization of these extracted strings is not detailed, but the risk is minimized by the skill's non-executable output format (JSON/Avro schemas and Markdown reports).
Audit Metadata