aot-trimming
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and provide guidance on user-supplied .NET source code and project configuration files. Processing untrusted external code represents a surface for indirect prompt injection.\n
- Ingestion points: User-provided C# source code and MSBuild project files analyzed by the agent.\n
- Boundary markers: The skill does not define specific delimiters for separating user code from agent instructions.\n
- Capability inventory: The skill provides instructions for build commands (dotnet publish) but does not include scripts with autonomous execution capabilities.\n
- Sanitization: No specific input sanitization or validation logic is defined within the skill documentation.\n- [EXTERNAL_DOWNLOADS]: The skill references technical documentation and error code tables from official Microsoft and .NET runtime sources. These are trusted technical resources used for legitimate developer guidance.
Audit Metadata