azure-eventgrid-py
Warn
Audited by Gen Agent Trust Hub on Feb 14, 2026
Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (MEDIUM): The skill facilitates the ingestion of untrusted data into event payloads that are subsequently published to Azure Event Grid.
- Ingestion points: Event data fields in
CloudEventandEventGridEventconstructors (e.g.,data=,subject=). - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat event payload content as untrusted.
- Capability inventory: The skill utilizes
EventGridPublisherClient.send()to perform outbound network operations to Azure endpoints. - Sanitization: No sanitization or validation logic is present in the examples or documentation to mitigate malicious content in the event data.
- [Unverifiable Dependencies] (LOW): The skill installs the
azure-eventgridandazure-identityPython packages. - Evidence:
pip install azure-eventgrid azure-identityinSKILL.md. - Trust Status: Downgraded to LOW per [TRUST-SCOPE-RULE] as these are official packages from a trusted organization (Azure/Microsoft).
- [Data Exposure & Exfiltration] (SAFE): The skill correctly uses
DefaultAzureCredentialfor authentication and utilizes environment variables for endpoints, avoiding hardcoded secrets or sensitive local file access.
Audit Metadata