build-parallelism
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Execution: The skill instructs the agent to execute standard .NET CLI and MSBuild commands (e.g.,
dotnet build /bl,dotnet msbuild) to generate and analyze performance logs. These commands are necessary for the skill's diagnostic functionality. - Indirect Prompt Injection Surface: The agent is guided to ingest and analyze external build logs (
.binlog). * Ingestion points: Data enters the context via binary log files referenced in analysis steps. * Boundary markers: No explicit delimiters or instructions to ignore embedded content are provided. * Capability inventory: The skill uses shell commands and specialized analysis tools (Microsoft.AITools.BinlogMcp) to process build data. * Sanitization: There is no mention of sanitizing or escaping content extracted from logs before the agent processes it. This represents a typical surface for agents dealing with external logs.
Audit Metadata