azure-eventgrid-java
Pass
Audited by Gen Agent Trust Hub on Apr 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection Surface: The skill includes patterns for ingesting untrusted data by parsing JSON event payloads from external sources.
- Ingestion points:
SKILL.mdandreferences/acceptance-criteria.mddemonstrate parsing JSON strings intoEventGridEventandCloudEventobjects using the SDK's built-in methods. - Boundary markers: No explicit instructions or delimiters are provided to the agent to treat the parsed content as untrusted data or to ignore potential instructions embedded within the payload.
- Capability inventory: The skill allows the agent to perform network operations through the
client.sendEvent()andclient.sendEvents()methods. - Sanitization: The implementation leverages strongly-typed Java classes for data mapping, which provides an inherent validation layer for the structure of the incoming data.
- Secure Authentication Practices: The documentation correctly emphasizes the use of
DefaultAzureCredentialand environment variables for managing topic endpoints and access keys, which follows recommended security protocols to prevent credential exposure.
Audit Metadata