The Agent Skills Directory

[SAFE]: The skill serves as a technical reference for .NET application security. It provides standard hardening configurations and code snippets (e.g., fallback authorization policies, HSTS configuration) that align with industry best practices.- [PROMPT_INJECTION]: No prompt injection patterns were detected. The skill uses instructional language consistent with its purpose as a security guide and does not attempt to override agent safety protocols.- [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill specifically advises against storing secrets in source code or logging sensitive information such as PII, passwords, or keys.- [DYNAMIC_EXECUTION]: The skill explicitly warns against unsafe deserialization practices, such as the use of BinaryFormatter, SoapFormatter, and NetDataContractSerializer, which are known security vulnerabilities.- [COMMAND_EXECUTION]: The skill mentions standard CLI tools like dotnet list package and NuGet Audit for dependency scanning, which are legitimate and safe uses of command-line utilities for development and auditing.- [INDIRECT_PROMPT_INJECTION]: The skill defines a clear structure for its output (a findings table) and specific categories for analysis, which mitigates the risk of the agent being misdirected by content in the code it is reviewing. It includes a mandatory evidence chain for its analysis surface.

dotnet-security