The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the dotnet utility, including dotnet add, dotnet remove, dotnet restore, and dotnet package search for managing .NET dependencies.
[INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted data from multiple sources, which constitutes a potential vulnerability surface.
Ingestion points: The skill ingests package identifiers and version strings from user requests, and reads data from project files such as .csproj and Directory.Packages.props (SKILL.md).
Boundary markers: There are no specific delimiters or instruction guardrails used when the agent interprets content from project files or user input.
Capability inventory: The skill utilizes the dotnet CLI for package operations and performs file modifications to project configurations (SKILL.md).
Sanitization: No input validation or escaping mechanisms are described for package names or versions before inclusion in shell commands.

nuget-manager