deep-research

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). This skill explicitly instructs the agent to use WebSearch, WebFetch and a Playwright browser to fetch and read content from public websites (including forums/Stack Overflow and other web pages) as part of its research workflow, exposing it to untrusted third-party content that could carry indirect prompt-injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:46 PM