oneshot

Warn

Audited by Snyk on Feb 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The workflow explicitly allows a "Quick WebSearch" during EXPLORE, meaning the agent may fetch and read open/public web content (untrusted third‑party sites) to gather API/library information as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:48 AM