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). The execution agent is explicitly instructed in Phase 2 to "Use WebSearch" and "Use WebFetch to read documentation" (Execution Agent prompt), which means the agent will fetch and read open/public third-party web content that may be user-generated and thus could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:57 AM