better-portuguese
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or remote dependencies. All components are descriptive markdown instructions or YAML configuration files.
- [PROMPT_INJECTION]: The instructions are focused exclusively on linguistic quality and stylistic consistency. There are no attempts to bypass safety filters, extract system prompts, or override agent constraints.
- [DATA_EXPOSURE]: The skill handles user-provided text and URLs for the purpose of translation and editing. It does not attempt to access sensitive file paths, environment variables, or hardcoded credentials. Ingestion of external content is restricted to its primary function as an editorial tool.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic code execution patterns are present. The skill relies entirely on natural language instructions for the agent.
Audit Metadata