multi-agent
Warn
Audited by Snyk on Feb 16, 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 explicitly defines a "researcher" worker with a "web_search" capability and system prompt to "gather information, find relevant sources, and cite your sources" (see SKILL.md quick start and scripts/orchestrator_worker.py WorkerConfig), which indicates the agent is expected to ingest and interpret untrusted public web content as part of its workflow.
Audit Metadata