flutter-worktrees
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using
git,flutter, anddartCLI tools. These include commands for creating worktrees (git worktree add), managing dependencies (flutter pub get), running code generation (dart run build_runner), and executing tests or analysis (flutter test,flutter analyze).\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it operates on and processes data from the local repository.\n - Ingestion points: The agent interacts with and processes project files such as
pubspec.yaml, source code, and test files during setup, analysis, and testing phases (SKILL.md).\n - Boundary markers: There are no explicit boundary markers or instructions to treat project-provided content as untrusted data.\n
- Capability inventory: The skill leverages
git,flutter, anddartbinaries to perform file system operations, network requests for dependencies, and execution of project code (SKILL.md).\n - Sanitization: The instructions do not include steps for sanitizing or validating project-controlled configuration files or test scripts before execution.
Audit Metadata