The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes local git commands such as git rev-parse, git log, and git diff to analyze repository metadata and code changes. These are read-only operations designed to facilitate .NET compatibility analysis and do not modify repository state.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks because it ingests untrusted data from Git commit messages and diffs without employing specific boundary markers or sanitization logic.
Ingestion points: Local repository data retrieved via git log and git diff, as well as user-provided change descriptions processed in SKILL.md.
Boundary markers: No delimiters or "ignore instructions" warnings are utilized when interpolating external commit data into the agent context.
Capability inventory: Execution of local git subprocesses.
Sanitization: No validation or filtering is performed on the content of commit messages or diffs before processing.
[EXTERNAL_DOWNLOADS]: Refers to official Microsoft .NET compatibility guidelines and library change rules. These references target a well-known service and do not involve the download or execution of remote scripts or packages.

dotnet-change-impact