agent-orchestration

Warn

Audited by Snyk on Mar 10, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This skill's Research Agent template explicitly instructs agents to gather and verify information from web sources (e.g., "Gather: Use available tools to collect information from multiple sources", "Search budget: {{search_limit}} web searches", and "Track and cite all sources" in templates/research-agent.md), meaning the agent will fetch and interpret untrusted public web content which can materially influence its actions and tool use.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 08:08 PM