The Agent Skills Directory

Standard Development Guidance: The skill consists of instructional markdown files providing architectural patterns, middleware ordering, and feature selection advice aligned with official documentation. These are purely informative and contain no executable code or malicious instructions.
Security Best Practices: The reference files explicitly recommend secure practices, including the use of Secret Manager for development, enforcing HTTPS, and applying the principle of least privilege in authentication and authorization contexts.
Inherent Indirect Prompt Injection Surface: As a development tool, this skill possesses an attack surface for indirect prompt injection.
Ingestion points: The agent reads and reviews local project files and source code as part of its primary workflow (documented in SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands in analyzed files are provided.
Capability inventory: The skill involves shell command execution of the .NET CLI (e.g., dotnet new in SKILL.md and stack-selection.md, and dotnet publish in testing-performance-and-operations.md).
Sanitization: No explicit sanitization or filtering of the analyzed content is mentioned in the instructions.
Context: This risk is inherent to any tool that analyzes untrusted code and is considered a standard operational consideration for this use case.
Consistent Internal Versioning: The instructions reference future-dated versions (e.g., .NET 10 and March 2026). This appears to be a deliberate part of the skill's specific context or environment and does not pose a security risk, though it may result in references to APIs not yet available in current real-world environments.

aspnet-core