UX Patterns Global

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill explicitly references and directs the agent to external public pages (e.g., "Site index: https://uxpatterns.dev/llms-full.txt" in SKILL.md and numerous https://uxpatterns.dev/ pattern URLs and GitHub install commands in references/categories.md), meaning the agent is expected to fetch and use third-party site content that can influence pattern-selection and follow-up actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill includes install commands like "npx skills add https://github.com/thedaviddias/ux-patterns-for-developers --skill …", which would fetch and execute remote code at runtime from the GitHub repo (https://github.com/thedaviddias/ux-patterns-for-developers), making it a required external dependency that could directly control agent behavior.