get-migration-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- Credential Management: (1) The skill acquires and manages Azure Resource Manager (ARM) access tokens to interact with Azure APIs. (2) While handling credentials requires care, the skill explicitly directs the agent to avoid logging tokens and ensures they are cleared from memory, which aligns with security best practices for credential handling.
- Indirect Prompt Injection Surface: (1) The skill processes data retrieved from the Azure Resource Graph, representing a potential ingestion surface for external content. (2) Ingesting external data is a consideration because it could theoretically be used to influence agent behavior. Evidence chain: [Ingestion points]: Data enters via ARG queries; [Boundary markers]: No explicit delimiters are used for the retrieved data; [Capability inventory]: The skill can perform network requests and manage files; [Sanitization]: Data is parsed as structured JSON but content validation is not explicitly defined.
Audit Metadata