dotnet-dependency

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (SAFE): The skill utilizes standard dotnet CLI commands and grep for analyzing project structures and managing dependencies. These are expected and safe operations for a development-focused skill.\n- EXTERNAL_DOWNLOADS (LOW): Facilitates the installation of NuGet packages and third-party global tools like dotnet-outdated-tool. Although these are core functions of the skill, they involve the acquisition of external code. The severity is lowered to LOW as this aligns with the primary intended purpose.\n- PROMPT_INJECTION (LOW): An indirect prompt injection surface is present because the agent processes external data from package search results and dependency lists. \n
  • Ingestion points: Output from dotnet package search and dotnet list package.\n
  • Boundary markers: Partially present; the skill recommends the --format json flag for several commands, which helps structure the data for the agent.\n
  • Capability inventory: Ability to install packages (dotnet add package) and tools (dotnet tool install).\n
  • Sanitization: Absent; there are no specific instructions or filters to prevent the agent from being influenced by malicious text embedded in package metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:50 PM