The Agent Skills Directory

[COMMAND_EXECUTION] (HIGH): The skill instructs the agent to execute dotnet build and dotnet test commands. These utilities execute arbitrary code contained within target .NET projects. An attacker providing a malicious project path or crafted filter strings could achieve unintended code execution within the agent's environment.
[Indirect Prompt Injection] (HIGH):
Ingestion points: User-controlled strings for project paths and filter expressions (FullyQualifiedName, DisplayName) are interpolated into shell commands across SKILL.md and reference files.
Boundary markers: Absent. The skill does not implement delimiters or safety instructions to prevent the agent from interpreting instructions embedded within user-provided data.
Capability inventory: Full subprocess execution for dotnet CLI (build, test, and dump analysis) and shell utilities like grep as seen in SKILL.md.
Sanitization: Absent. There is no evidence of input validation, escaping, or path normalization for the user-provided values before they are passed to the shell.

dotnet-test