dotnet-inspect-decompiler

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via the dnx utility to run the dotnet-inspect tool. These commands are used to perform assembly decompilation, metadata inspection, and code search (e.g., dnx dotnet-inspect -y -- type ...).
  • [EXTERNAL_DOWNLOADS]: By default, the tool may access the network to acquire NuGet packages and PDB (symbol) files from remote registries to facilitate SourceLink mapping and detailed symbol resolution. The documentation explicitly mentions the --offline flag to disable this network behavior when necessary.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill ingests untrusted data in the form of compiled .NET assemblies, PDB files, and external packages provided via CLI arguments like --package, --platform, or --library.
  • Boundary markers: The instructions do not define specific delimiters for the tool's output or provide explicit warnings to the agent to disregard instructions that might be embedded in decompiled code comments or string literals.
  • Capability inventory: The agent has the capability to execute shell commands via dnx and read/write local project files via the --project and output redirection flags.
  • Sanitization: There is no explicit sanitization step mentioned for the decompiled C# or IL output before it is processed by the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 09:26 AM