build-perf-diagnostics

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution: The skill instructs the agent to use standard development tools such as the dotnet CLI and grep. These are used appropriately within the context of build diagnostics (e.g., generating binary logs and searching text summaries for performance metrics).
  • Data Processing: The analysis methodology involves processing MSBuild binary logs (.binlog) and text-based diagnostic logs. This is standard practice for performance tuning and does not involve accessing sensitive user credentials or system files.
  • Bundled Tooling: The skill references a bundled MCP server (Microsoft.AITools.BinlogMcp). This tool appears to be an integrated part of the skill's environment for specialized log parsing, which is a routine extension of its diagnostic capabilities.
  • Indirect Prompt Injection Consideration: As a diagnostic tool that processes external logs, there is a theoretical surface for indirect prompt injection if a log contained malicious instructions. However, the skill's instructions focus on extracting quantitative timing data and performance summaries, which significantly minimizes the risk of the agent interpreting log content as commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 05:47 PM