ai-agent-orchestrator

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 ResearchAgent is explicitly configured with searchTool and webScrapeTool to search, scrape, and gather information from the open web (e.g., public websites) and is expected to read and summarize those untrusted, user-generated sources as part of its workflow (see ResearchAgent tools and the example workflow task "Research the latest AI trends in 2024"), creating a clear vector for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:54 PM