The Agent Skills Directory

[SAFE] (SAFE): No malicious patterns or security risks were identified in the skill's instructions or code snippets. The code examples use standard Kafka libraries and connect to local instances.
[Indirect Prompt Injection] (LOW): The skill defines tools for reading and processing Kafka stream data. This represents a potential indirect prompt injection surface if the agent consumes data from untrusted external topics.
Ingestion points: KafkaConsumer logic in SKILL.md used to read from Kafka topics.
Boundary markers: None present in the provided code snippets.
Capability inventory: Bash, Write, Edit tools are permitted.
Sanitization: No explicit sanitization or validation of the message payload is shown in the examples.

kafka-expert