youdotcom-cli

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and live-crawl public web pages via https://api.you.com (search/research with livecrawl) and https://ydc-index.io/v1/contents for arbitrary URLs and then pass that "" into the agent's reasoning workflow (see Workflow and Examples), so untrusted third‑party page content can influence decisions and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill issues runtime curl requests to You.com endpoints (e.g., https://api.you.com/v1/research and https://ydc-index.io/v1/contents) and explicitly injects the returned content into the agent context as ..., meaning externally fetched content at runtime can directly influence prompts/behavior.