The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the dotnet CLI to perform essential migration tasks, including dotnet sln list for discovery, dotnet build for validation, and dotnet new packagesprops for file generation. It also utilizes search utilities like grep or PowerShell's Select-String to audit property usage across the codebase.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and parse untrusted data from the user's repository.
Ingestion points: The workflow involves reading and auditing project files (.csproj, .fsproj, .vbproj), solution files (.sln, .slnx), and MSBuild configuration files (.props, .targets) to extract package references and property values.
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the untrusted project data from the agent's logic.
Capability inventory: The agent has the capability to write files (e.g., creating Directory.Packages.props, updating project XML, and generating a markdown report) and execute build-related commands (dotnet clean, dotnet restore, dotnet build).
Sanitization: No explicit sanitization or validation logic is defined to check for malicious instructions embedded within the target repository's files before they are parsed or used to trigger build operations.

convert-to-cpm