ux-copy

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were identified. The skill consists entirely of instructional markdown content and documentation for copywriting interface text.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided interface copy to perform reviews and rewrites, creating a potential surface for indirect prompt injection. This is a low-risk surface inherent to the skill's primary purpose.
  • Ingestion points: User-supplied product messages, UI strings, and notifications for review (SKILL.md).
  • Boundary markers: None present in the instructions to delimit user input from agent instructions.
  • Capability inventory: The skill is restricted to text analysis and generation within the conversation context; it does not request network access or file system modifications.
  • Sanitization: No explicit sanitization or filtering of external content is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 12:19 PM
Security Audit — agent-trust-hub — ux-copy