sota-ux-writing

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides structured guidance for UX writing and content design, adhering to industry standards like ISO 24495-1 and WCAG 2.2.
  • [SAFE]: It includes static analysis patterns using grep to scan for common UX copy issues (e.g., filler words, generic errors, and concatenated plurals). These commands are executed locally, use hardcoded regex patterns, and are limited to the skill's intended auditing tasks.
  • [SAFE]: The skill incorporates security-conscious instructions, specifically directing the agent to audit for sensitive data leaks in error messages (such as stack traces, paths, or hostnames) and to prevent user enumeration in authentication flows.
  • [INDIRECT_PROMPT_INJECTION]: The skill audits user-provided product copy and localization files, creating a potential ingestion surface. 1. Ingestion points: Evaluation of *.json, *.po, *.strings, and other localization files, as well as hardcoded literals in source code. 2. Boundary markers: Not explicitly defined for the audited content. 3. Capability inventory: Use of grep for local filesystem scanning and pattern matching. 4. Sanitization: Not specified for the content being audited.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 10:22 AM