every-style-check
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is limited to text processing and generating an editorial checklist. It does not request any tools or permissions that would allow for network access, file system modification, or command execution.
- [SAFE]: All reference materials used by the skill (
every-style-guide.mdandevery-editing-principles.md) are stored locally within the skill's directory, ensuring no external dependencies or remote content are fetched during operation. - [DATA_EXPOSURE]: No hardcoded secrets, credentials, or sensitive file paths were found. The skill instructions prioritize proper formatting and linking of public information (like author pages and research sources).
- [PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, such as attempts to bypass safety filters, override agent behavior, or extract system instructions. The 'Important Notes' are purely editorial in nature.
- [REMOTE_CODE_EXECUTION]: There is no evidence of remote script downloading, package installation, or dynamic code execution logic in any of the provided files.
Audit Metadata