eval-performance
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local shell commands, including
dotnet msbuildandgrep, to generate and analyze build diagnostics. These commands are standard for MSBuild development but execute against local project files and logs. - [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves ingesting and analyzing untrusted external data such as MSBuild binary logs (.binlog), preprocessed project XML, and diagnostic text logs. These sources could be manipulated to include instructions designed to mislead the agent during the analysis process.
- Ingestion points: MSBuild binary logs, text logs, and preprocessed project files as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore content embedded within the logs being analyzed.
- Capability inventory: The skill utilizes shell commands (
dotnet msbuild,grep) and Model Context Protocol (MCP) tools (Microsoft.AITools.BinlogMcp) for log analysis. - Sanitization: No explicit sanitization or validation of the log content is described before the agent processes it.
Audit Metadata