mielui

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

• Third-party content exposure detected (low risk: 0.10). The skill requires fetching https://ui.miel.my/llms.txt and component pages from URLs listed within it at runtime, allowing potential indirect prompt injection from fetched remote content.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references https://ui.miel.my/llms.txt and https://ui.miel.my/llms-full.txt as runtime operational dependencies fetched to obtain instructions, component references, and behavior-selecting configuration for the agent, and miel.my is an unverified, unofficial custom domain lacking strong publisher provenance.