scaffold-dotnet-test-project

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to search for and interpret instructions from a repository-resident file (.agents/skill-overlays/dotnet-test/scaffold-dotnet-test-project.md). This creates an attack surface where instructions embedded in a project's files can influence the agent's logic.
  • Ingestion points: The agent is instructed to read the file located at .agents/skill-overlays/dotnet-test/scaffold-dotnet-test-project.md before starting discovery.
  • Boundary markers: The skill mandates a frontmatter check requiring specific values for core, binding-revision, and mode. It also specifies that user instructions and project constraints override overlay settings.
  • Capability inventory: The skill possesses the capability to write to the filesystem and execute shell commands via the dotnet CLI.
  • Sanitization: There is no mention of sanitization or escaping for the content read from the overlay file.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of multiple .NET CLI commands, including dotnet new, dotnet add reference, dotnet sln, and dotnet test. While these are expected for the skill's primary purpose, they represent a significant capability tier that interacts with the user's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 07:34 AM
Security Audit — agent-trust-hub — scaffold-dotnet-test-project