migrate-vstest-to-mtp

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from repository files to guide the migration process.\n
  • Ingestion points: The agent is instructed to discover and read project files (.csproj, .sln, .slnx), build configuration (Directory.Build.props), SDK configuration (global.json), and CI/CD pipeline definitions (YAML).\n
  • Boundary markers: There are no instructions to use delimiters or ignore potential instructions embedded within the content of the processed repository files.\n
  • Capability inventory: The agent has broad capabilities including file discovery, reading and editing project files, and executing shell commands (specifically dotnet test, dotnet build, and direct execution of test binaries).\n
  • Sanitization: No instructions are provided for sanitizing or validating the content of the ingested files before they are used to influence the agent's migration plan or actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:11 AM