agent-loops

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: 0.90). The skill includes a 'search_web' tool in scripts/agent-workflow-template.ts (and uses it in examples like exampleReActAgent/exampleFunctionCalling and the multi-agent Researcher) that fetches open web results which the agent ingests and interprets, exposing it to untrusted public third-party content and potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:22 PM