ux-writing
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external project files and UI code to perform its text analysis, which creates a surface for indirect prompt injection if those files contain adversarial content.
- Ingestion points: Reads content from project source code, screen copy, and design files as specified in the skill's arguments or discovered in the project context.
- Boundary markers: The skill instructions mandate using a structured before/after table format for proposals and require explicit user approval before any file modifications.
- Capability inventory: The skill possesses the ability to read project files and write string replacements to the local filesystem.
- Sanitization: While there is no explicit sanitization of the input strings mentioned, the transformation logic is governed by a defined set of UX writing principles, and the final application of changes is gated by human review.
Audit Metadata