deep-research

Warn

Audited by Snyk on Jun 18, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.95). The required runtime workflow uses websearch to collect arbitrary public web URLs and then webfetch to fetch and read the fetched pages’ body text into the agent for synthesis, which is outsider-authored free text from the public web.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 18, 2026, 04:42 PM
Issues
1
Security Audit — snyk — deep-research