neon

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

• Third-party content exposure detected (high risk: 0.95). The required runtime step is WebFetch("https://neon.com/llms.txt"), which fetches public web content and feeds the fetched free text into the agent’s LLM context (public outsider-authored page).

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

• Potentially malicious external URL detected (high risk: 1.00). The skill explicitly requires fetching and using live external instructions at runtime via WebFetch("https://neon.com/llms.txt"), so the remote content directly controls the agent's behavior and is a required runtime dependency.