mcaf-dotnet-code-analysis
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and follow instructions from external, repository-supplied files, creating a surface for indirect prompt injection.
- Ingestion points: Reads instructions from the repository's
AGENTS.mdfile and configuration data from.csprojandDirectory.Build.propsproject files. - Boundary markers: Absent. No instructions are provided to the agent to distinguish between its own system instructions and potentially malicious directives found in these external files.
- Capability inventory: The skill uses the shell to execute
dotnetandrgcommands as specified inSKILL.md. - Sanitization: Absent. The skill does not validate or filter the content of
AGENTS.mdbefore adhering to its scoped commands. - [COMMAND_EXECUTION]: Utilizes standard CLI tools to perform its tasks. It executes
dotnet build,dotnet --info, andrg(ripgrep) to gather environment information, search for configuration strings, and verify analyzer implementation. These operations are restricted to project-specific files and standard .NET SDK functionality.
Audit Metadata