azure-eventgrid-java
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official
com.azure:azure-messaging-eventgridMaven package from Microsoft, which is a trusted and well-known source. - [PROMPT_INJECTION]: The skill demonstrates the ingestion of untrusted data from external events, which presents a surface for indirect prompt injection.
- Ingestion points: Logic for parsing JSON payloads into
EventGridEventandCloudEventobjects is present inSKILL.mdandreferences/acceptance-criteria.md. - Boundary markers: No delimiters or specific instructions for the agent to ignore content within the data are provided in the examples.
- Capability inventory: The code examples focus on event publication and console output; no critical capabilities like shell execution or unauthorized file access were found in the ingestion logic.
- Sanitization: No explicit sanitization or validation logic for the ingested event data is shown in the provided examples.
Audit Metadata