NYC

openai-agents

Warn

Audited by Snyk on Feb 15, 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 skill references a built-in webSearchTool and examples that call external search APIs (references/common-errors.md Error 8 and related examples showing fetch to external search endpoints), which means agents can ingest open/public web search results or third‑party API responses and then read/interpret that untrusted user-generated content as part of their workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:02 PM