azure-eventgrid-java
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Azure Event Grid payloads), creating a surface for potential instruction injection through event content.
- Ingestion points: Event data is ingested via
EventGridEvent.fromString(jsonPayload)andreceiverClient.receive(...)as shown inSKILL.md. - Boundary markers: None. The provided code snippets do not implement delimiters or instructions to ignore embedded commands in the event data.
- Capability inventory: The skill allows the agent to publish new events, acknowledge/reject messages, and interact with Azure services via the SDK in
SKILL.md. - Sanitization: None. The implementation examples show direct parsing and object conversion (e.g.,
data.toObject(OrderData.class)) without validation or sanitization of the content before use in further logic.
Audit Metadata