youmind

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt shows and encourages embedding API keys verbatim (e.g., export YOUMIND_API_KEY=sk-ym-xxx and --api-key sk-ym-xxx), and explicitly allows passing secrets as command-line arguments, which requires the agent to handle/output secret values directly.

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

• Third-party content exposure detected (high risk: 0.90). The skill issues requests to the YouMind API (default endpoint https://youmind.com) via the youmind CLI (e.g., youmind search/youmind call) to fetch and manage user-generated content such as boards, notes, and picks, which the agent is expected to read and could therefore contain untrusted instructions that influence its actions.