unit-test-generator
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute various shell commands including 'find' for file scanning, 'mkdir' for directory setup, and 'flutter test' for validation. It also automates Git workflows using 'git add', 'git commit', and 'git push' to manage test code changes.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the source code files it processes.\n
- Ingestion points: The agent reads '.dart' files from the 'lib/' directory to identify test targets.\n
- Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the source code comments.\n
- Capability inventory: The agent has access to 'Bash' execution, filesystem 'Write' access, and 'Git' network capabilities.\n
- Sanitization: No sanitization or validation of the input source code content is performed prior to analysis.\n- [EXTERNAL_DOWNLOADS]: The skill references and requires external dependencies from the Flutter/Dart ecosystem, specifically 'flutter_test', 'mockito', and 'build_runner'.
Audit Metadata