dotnet-aot-compat

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [Command Execution]: The skill utilizes standard .NET development tools, including dotnet build and grep, to identify and filter IL-related warnings. These commands are executed within the context of the project's build environment to guide the compatibility resolution process. This is a standard practice for development-focused skills.
  • [Indirect Prompt Injection Surface]: The skill involves reading and processing source code files and compiler output, which represents a potential surface for indirect prompt injection if the files originate from untrusted sources.
  • Ingestion points: The agent reads .cs and .csproj files, as well as the text output from the dotnet build command.
  • Boundary markers: No specific delimiters or markers are defined to separate untrusted file content from the agent's instructions.
  • Capability inventory: The skill possesses the capability to modify local files and execute shell commands through the development environment.
  • Sanitization: The skill relies on standard agent processing without additional validation of the source code content.
  • Context: This risk is inherent to any skill that automates code refactoring or remediation. Users should ensure they are working with projects from trusted sources when using these capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:35 AM