The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to build and review C# applications, creating an attack surface where instructions could be embedded in the data processed by the generated applications.
Ingestion points: The skill provides templates for ASP.NET Core API endpoints and Blazor forms that ingest external user data (found in references/aspnet-core.md and references/blazor.md).
Boundary markers: The instructions do not explicitly mandate the use of delimiters or boundary markers for the agent when handling data from these ingestion points.
Capability inventory: The skill possesses capabilities to write source code, configure database schemas, and execute .NET CLI commands (SKILL.md).
Sanitization: The skill mitigates this risk by explicitly mandating input validation as a constraint and providing implementation examples using DataAnnotationsValidator and FluentValidation patterns.
[EXTERNAL_DOWNLOADS]: The skill references an external documentation resource hosted on a well-known service.
Evidence: SKILL.md contains a reference to https://jeffallan.github.io/claude-skills/skills/language/csharp-developer/ for extended documentation. This resource is owned by the skill author and hosted on a well-known platform.
[COMMAND_EXECUTION]: The skill instructs the agent to execute standard development CLI tools.
Evidence: SKILL.md includes a workflow checkpoint that directs the agent to run dotnet ef migrations add and dotnet ef migrations remove for database management.
Context: These are standard operations within the .NET ecosystem, and the skill includes explicit instructions for the agent to review changes before applying them to ensure safety.

csharp-developer