dotnet-aot-compat
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill instructs the agent to execute shell commands such as
dotnet buildandgrepto identify compilation warnings. This is a standard and necessary part of the skill's intended purpose for .NET project maintenance. - Indirect Prompt Injection Surface: The skill processes external data in the form of build output and project source code to drive its iterative fix process. While this creates an ingestion point for untrusted data, the skill includes specific strategies and code patterns to ensure changes are applied safely and correctly within the .NET ecosystem.
- Metadata and Logic Consistency: The skill's claimed purpose (Native AOT compatibility) aligns perfectly with its instructions and the provided C# code snippets. It correctly identifies and advises against unsafe practices like manual warning suppression, favoring robust attribute-based solutions.
Audit Metadata