flutter-slang-i18n
Pass
Audited by Gen Agent Trust Hub on Aug 9, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs local shell operations including
git status,flutter pub add, anddart runto manage localization dependencies and generate code. It also executes a provided Python script (scan_dart_strings.py) to analyze the target project's source code. These are typical operations for a development-focused skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning arbitrary Dart source files within the user's project.
- Ingestion points: The
scripts/scan_dart_strings.pyutility reads content from all.dartfiles in the target project root (excluding standard build/tool directories). - Boundary markers: Instructions explicitly direct the agent to "Treat scanner output as candidates, not truth" and to "Review surrounding code before changing anything," providing behavioral safeguards against blindly following embedded instructions.
- Capability inventory: The skill possesses the ability to execute shell commands, create configuration files, and modify existing application source code.
- Sanitization: The script extracts string literals using regex and state-machine logic but does not perform content sanitization before presenting findings to the agent's context.
Audit Metadata