clarify
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions and documentation for text improvement. It does not include scripts, binaries, or command-line executions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and refine user-provided text (copy, labels, error messages). While this represents an ingestion of untrusted data, the skill has no associated tools or capabilities (such as network access or file system modification) that could be exploited through malicious instructions in the input text.
- [SAFE]: External references are limited to local markdown files within the repository's project structure (e.g.,
../frontend-design/reference/ux-writing.md), which are used for additional context and consistency.
Audit Metadata