vite

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs the agent to "Fetch live documentation for up-to-date details" and provides an external Docs link (https://vite.dev/llms.txt), which means the agent would fetch and interpret public third‑party web content that could influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly states it will "Fetch live documentation for up-to-date details" and lists the Docs URL https://vite.dev/llms.txt, indicating the agent will fetch that external text at runtime and likely inject or rely on it to build prompts/instructions, so the external content can directly control the agent's behavior.