The Agent Skills Directory

[SAFE]: The skill incorporates a robust security directive preventing the agent from reading or displaying sensitive .env files, which effectively mitigates the risk of credential exposure.\n- [EXTERNAL_DOWNLOADS]: All external dependencies, including Docker images (confluentinc/confluent-local, confluentinc/cp-schema-registry) and Python packages (confluent-kafka), are official resources from the vendor and are appropriate for the skill's functionality.\n- [DATA_EXFILTRATION]: Network activity defined in the reference code is restricted to legitimate administrative health checks and message production/consumption against user-defined Kafka clusters. No suspicious exfiltration of user data was observed.\n- [PROMPT_INJECTION]: The skill does not attempt to bypass safety filters or override system instructions. It uses a structured requirement-gathering phase to ensure agent actions are aligned with user intent.\n- [COMMAND_EXECUTION]: The instructions do not involve the execution of arbitrary or dangerous system commands.

developing-kafka-python-client