mcaf-dotnet

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell-level operations for .NET project lifecycle management, including executing build, test, format, and analyze commands. It also includes instructions to install .NET tools if they are missing from the environment.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it prioritizes command definitions and instructions found within a repository-controlled AGENTS.md file.
  • Ingestion points: Reads project configuration (.csproj, Directory.Build.*) and the local AGENTS.md file from the repository.
  • Boundary markers: The instructions do not define any delimiters or warning markers to help the agent distinguish between trusted instructions and untrusted repository data.
  • Capability inventory: The skill has the capability to execute shell commands across all scripts and referenced files for building, testing, and tool management.
  • Sanitization: There is no evidence of input validation or command sanitization for the commands retrieved from the repository files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 04:09 PM
Security Audit — agent-trust-hub — mcaf-dotnet