TailAdmin UI Patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to git clone and read files from the public GitHub repository "https://github.com/TailAdmin/tailadmin-free-tailwind-dashboard-template" (e.g., /tmp/tailadmin/src/ and tailwind.config.js), which is open/public third-party content the agent is expected to ingest and could contain untrusted user-provided data.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly requires performing a runtime git clone of https://github.com/TailAdmin/tailadmin-free-tailwind-dashboard-template.git and then reads those repository files as the authoritative, required source that directly determines the agent's implementation instructions and class usage, so the fetched content controls the agent's behavior.