youdotcom-cli

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests untrusted third-party web content via ydc search with "livecrawl":"web" and ydc contents from arbitrary URLs (see the SKILL.md examples and the "Safety rule" / "Handle Results Safely" sections), meaning the agent will read external user-generated or public web pages that could contain indirect prompt-injection content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 05:07 AM