ddd4j-javalin-mq
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The file references/source-evidence.md contains a hardcoded absolute file path (/Users/wandl/workspaces/workspace-ddd4j/workspace-ddd4j-boot/ddd4j-javalin) which exposes specific local system information including a username.- [INDIRECT_PROMPT_INJECTION]: The skill describes processing MQ messages from external brokers, which presents a surface for malicious data to influence agent behavior.
- Ingestion points: MQ listeners (e.g., PaymentListener, AnalyticsListener).
- Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings for external message content are defined.
- Capability inventory: The skill specifies capabilities for running publish/consume, recovery, and shutdown tests against a real broker.
- Sanitization: The instructions lack explicit programmatic sanitization or filtering logic for external message content.
Audit Metadata