building-streaming-pipelines
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing standard, well-known Python libraries including
confluent-kafka,paho-mqtt, andnats-pyfor stream processing. These are industry-standard packages from reputable maintainers. - [INDIRECT_PROMPT_INJECTION]: The skill instructions cover consuming data from external event streams (Kafka topics, MQTT brokers, NATS subjects). This involves processing untrusted external data, which is an inherent part of the skill's primary purpose. The provided patterns include best practices such as schema validation and dead-letter queues to handle malformed or unexpected data safely.
- [COMMAND_EXECUTION]: Code examples include administrative operations like creating topics and managing consumer groups. These are standard operations for the described streaming platforms and are intended for local infrastructure management.
- [DATA_EXFILTRATION]: The skill references a well-known public test broker (
broker.emqx.io) for MQTT development. All other network operations target local infrastructure or official service endpoints.
Audit Metadata