youmind-deep-research

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses the YouMind CLI to conduct research and retrieve messages via listMessages, which fetches reports and data from the third-party YouMind service containing untrusted external research content.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of @youmind-ai/cli via npm, which is a common/reputable unofficial package and tooling channel.