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, and blob data referenced in SKILL.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
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:11 PM
Security Audit — agent-trust-hub — azure-functions