dotnet-inspect-performance

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands, such as dnx dotnet-inspect for assembly analysis and dotnet run --project src/runfaster for trace correlation. These are used to process user-specified files and external code within the local environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data through .NET assemblies (.dll) and performance trace files (.nettrace).
  • Ingestion points: External files are provided via command-line arguments to the analysis tools.
  • Boundary markers: None identified to prevent the agent from following instructions embedded in method names or metadata within processed binaries.
  • Capability inventory: Execution of shell commands and file writing capabilities are present.
  • Sanitization: None described for tool output before agent consumption.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 10:38 PM
Security Audit — agent-trust-hub — dotnet-inspect-performance