azure-eventhub-java

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill enables the agent to ingest and process external data streams from Azure Event Hubs, creating a surface where untrusted input could influence behavior if not properly handled.
  • Ingestion points: Data is ingested via event.getBodyAsString() and event.getProperties() in SKILL.md and references/examples.md.
  • Boundary markers: The provided examples do not demonstrate explicit delimiters to separate untrusted event content from agent instructions.
  • Capability inventory: The skill includes capabilities for logging to the console and managing state through checkpoints and partition properties.
  • Sanitization: The example code does not implement specific validation or sanitization of the event payloads before they are processed or logged.
  • Trusted SDK Dependencies: The skill utilizes official Maven dependencies from Microsoft (e.g., com.azure:azure-messaging-eventhubs), which are standard for Azure development. All external service references target well-known Azure endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-eventhub-java