azure-functions
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill documentation includes examples for creating functions that ingest untrusted data from external sources.
- Ingestion points:
request.json(),request.params.source,queueItem, andblobdata referenced inSKILL.md. - Capability inventory: Examples demonstrate logging, database writes to Cosmos DB, and task orchestration via Durable Functions.
- Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are present in the code snippets.
- Sanitization: The examples focus on functionality and do not include input validation or sanitization logic.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Azure CLI (
az) and Azure Functions Core Tools (func) for project initialization, resource creation, and deployment. These are standard tools for the intended primary purpose of the skill.
Audit Metadata