kafka
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external Kafka brokers, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent's context through the
Consumer.consume()method as shown inreferences/platformatic-kafka.mdandreferences/usage-guide.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content of messages retrieved from Kafka.
- Capability inventory: The agent is provided with capabilities for writing back to the cluster via
Producer.send()and executing administrative tasks through theAdminAPI. - Sanitization: There are no guidelines or code examples provided for sanitizing or validating the contents of Kafka messages before they are processed by the agent.
- [EXTERNAL_DOWNLOADS]: The skill references and recommends the installation of the
@platformatic/kafkalibrary from the npm registry. This is an established package provided by Platformatic, a well-known service in the Node.js development ecosystem.
Audit Metadata