synthesis-voice-profiler

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly says in Step 1 "If the user provides URLs, fetch and read them", so it ingests arbitrary public web content (untrusted/user-provided URLs) that it analyzes to generate a voice profile which can materially influence downstream tool behavior — creating a clear channel for indirect prompt injection.