The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes standard .NET CLI commands such as dotnet test to generate coverage reports. This is a common development task and does not involve executing untrusted remote code.
[SAFE]: Analysis of potential Indirect Prompt Injection surface: 1. Ingestion points: Local source files (.cs) and Cobertura XML reports. 2. Boundary markers: None used, as the skill performs direct metric calculation. 3. Capability inventory: Local file system read access and execution of the dotnet CLI. 4. Sanitization: The skill's logic is limited to counting decision points and parsing coverage percentages, which are low-risk operations for the data ingested.

crap-score