ceo-companion

Warn

Audited by Snyk on Feb 16, 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 requires using built-in WebSearch and WebFetch to fetch and analyze live public web content (e.g., Dribbble, Behance, App Store screenshots, forum threads, GitHub repos and arbitrary URLs) which are untrusted/user-generated and the agent is expected to read and interpret them for market research and design.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:25 AM