better-writing
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The instructions focus entirely on stylistic and functional guidelines for user interface text. There are no patterns observed that attempt to bypass safety filters, extract system prompts, or override core agent behavior. The specific formatting instructions for a 'Verdict' (Block/Approve) are scoped to the task of UX writing reviews and do not influence the agent's security posture.
- [DATA_EXPOSURE]: No hardcoded credentials, API keys, or sensitive file paths were detected. Examples within the skill use generic placeholders like 'name@example.com'.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any commands for downloading external scripts, installing packages, or executing remote code. It references sibling skills (e.g., better-accessibility) for context, but does not perform any network operations to fetch them.
- [COMMAND_EXECUTION]: There are no shell commands, subprocess invocations, or script generation patterns. The skill is purely informative and instructional.
Audit Metadata