csharp-developer
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
dotnet efCLI for database migration management, which involves executing shell commands in the user's environment as part of the standard .NET development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill performs analysis of local project files, such as
.csprojand NuGet package configurations, which may contain untrusted data that could influence the agent's behavior. - Ingestion points: Local project files, architecture metadata, and package definitions accessed during the "Analyze solution" workflow described in
SKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious content embedded in project file comments or metadata.
- Capability inventory: The skill guides the agent in writing code, configuring APIs, and executing shell commands via the
dotnetCLI. - Sanitization: No specific sanitization logic for external project content is described in the reference materials.
Audit Metadata