The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted repository files to determine configuration state.\n
Ingestion points: Reads .editorconfig, .globalconfig, and project files (.csproj, Directory.Build.*) using ripgrep in SKILL.md.\n
Boundary markers: No explicit instruction to ignore or delimit instructions found within the analyzed files.\n
Capability inventory: Capability to execute dotnet build and rg based on discovered configuration.\n
Sanitization: No sanitization of the content found in these files is performed before inclusion in the agent's context.\n- [COMMAND_EXECUTION]: The skill uses shell commands for repository inspection and build validation.\n
Evidence: Uses rg --files -g '.editorconfig' -g '.globalconfig' and dotnet build as part of the normal configuration workflow.

analyzer-config