skills/dotnet/skills/mtp-hot-reload/Gen Agent Trust Hub

mtp-hot-reload

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution Surface: The skill generates and suggests shell commands (e.g., dotnet run, dotnet add package) using user-supplied inputs such as project paths and test filters. This is a functional requirement for setting up and running tests but represents a surface where the execution environment depends on the validity of these inputs.
  • Indirect Prompt Injection Surface: The skill processes user-supplied data which is then interpolated into shell commands without explicit sanitization instructions.
  • Ingestion points: User-provided inputs for project paths and test names or filters defined in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the user inputs.
  • Capability inventory: The skill utilizes dotnet add, dotnet run, dotnet build, and dotnet watch to interact with the project environment.
  • Sanitization: There is no explicit mention of input validation or escaping for the user-provided strings before command generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:16 AM
Security Audit — agent-trust-hub — mtp-hot-reload