The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from local repository files, such as .csproj and .editorconfig, to automate the configuration and execution of .NET analysis tools. This behavior introduces an attack surface where malicious content within these files could attempt to influence the agent's behavior.
Ingestion points: SKILL.md (searches and reads .csproj, .editorconfig, and .config/dotnet-tools.json).
Boundary markers: Absent; the skill does not use explicit delimiters or instructions to isolate or ignore instructions embedded in the ingested data.
Capability inventory: SKILL.md (invokes dotnet build, dotnet add package, dotnet tool install, and various roslynator CLI commands).
Sanitization: Absent; there is no mention of validation or sanitization of the file contents before they are processed by the agent.
[COMMAND_EXECUTION]: The skill instructs the agent to execute several system commands to inspect the project environment and manage tools.
Evidence: SKILL.md specifies the use of rg (ripgrep) for searching, dotnet tool list for environment inspection, and dotnet tool install for setup tasks.

roslynator