alterlab-genai-sound-effects

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

• Third-party content exposure detected (high risk: 0.90). Yes — the skill's SKILL.md (Execution Mode, Workflow step 1, and Agentic Protocol) explicitly instructs the agent to "search the web" for current ElevenLabs features, prompt tips, and updates, requiring fetching and reading untrusted public web content that will be used to shape prompts and generation decisions.