dotnet-mstest

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a vulnerability to indirect prompt injection by design, as it prioritizes and executes commands found in the local configuration file.\n
  • Ingestion points: The skill reads the nearest AGENTS.md file within the repository to identify and execute the repo's real test command.\n
  • Boundary markers: No delimiters or boundary markers are present to isolate the external input from the agent's execution logic.\n
  • Capability inventory: The skill possesses the capability to execute shell commands via dotnet test, dotnet add, and rg (ripgrep).\n
  • Sanitization: No sanitization, validation, or human-in-the-loop verification is mentioned for the commands extracted from AGENTS.md.\n- [COMMAND_EXECUTION]: The skill relies on shell commands for its core functionality of managing and running .NET tests.\n
  • Evidence: The skill explicitly uses dotnet test, dotnet add package, and rg to perform project analysis and testing tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 12:41 PM
Security Audit — agent-trust-hub — dotnet-mstest