dotnet-inspect-performance
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of .NET assemblies (.dll), triage JSON files, and performance traces.
- Ingestion points: The skill ingests library files (e.g.,
MyLib.dll), triage configurations (triage.json), and nettrace files (workload.nettrace) through thedotnet-inspectanalysis tool. - Boundary markers: There are no explicit instructions or delimiters provided to the agent to disregard potentially malicious instructions or misleading metadata embedded within the IL (Intermediate Language) or metadata of the analyzed assemblies.
- Capability inventory: The skill utilizes shell commands (
dnx dotnet-inspect,dotnet run) to perform deep structural analysis, call graph generation, and performance triage. - Sanitization: The instructions do not specify any sanitization or validation of the content extracted from the target libraries before it is used to influence the agent's performance triage and optimization recommendations.
- [COMMAND_EXECUTION]: The skill is designed around the execution of shell-based CLI tools (
dnx,dotnet). - The commands include a
-yflag (e.g.,dnx dotnet-inspect -y), which typically suppresses confirmation prompts, potentially allowing the tool to perform actions without explicit user approval for each step.
Audit Metadata