skills/midudev/autoskills/aspnet-core/Gen Agent Trust Hub

aspnet-core

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided source code and project configurations to perform architectural reviews and refactoring, which serves as a potential surface for indirect prompt injection. This is an inherent risk factor for agents providing developer assistance and code review services.\n
  • Ingestion points: The agent ingests user-supplied .cs, .razor, and .cshtml files, along with project metadata, during the build and review workflow.\n
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded commands within the user-provided content.\n
  • Capability inventory: The agent can generate code, modify existing project files, and suggest the execution of .NET CLI commands (e.g., dotnet new, dotnet publish).\n
  • Sanitization: No specific sanitization or validation logic is implemented for the external code being processed.\n- [SAFE]: The skill relies exclusively on official, high-authority documentation and repositories from trusted organizations for framework guidance.\n
  • Evidence: References to Microsoft Learn and the official .NET Foundation GitHub repositories ensure that the guidance provided is safe and aligned with current industry best practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — aspnet-core