deep-research
Warn
Audited by Snyk on Sep 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The deep research workflow uses Codex CLI to perform web and data research across parallel child tasks, ingesting arbitrary web pages and fetched content into the agent's runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata