lipsync

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

• Third-party content exposure detected (low risk: 0.10). The skill workflow accepts user-provided media files, URLs, and social media links (such as YouTube, TikTok, Instagram, or Facebook links) and passes them into the third-party sync.so API for processing, which constitutes ingestion of outsider-authored content via URLs/links.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to install an external npm package (@sync.so/mcp-server@latest) at runtime via npx, which constitutes an unverifiable external runtime dependency with common/reputable unofficial provenance.