n8n-agents
Warn
Audited by Snyk on Jul 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). At runtime, the agent’s main input (
chatInput/ user message) is outsider-authored free text from the chat trigger (e.g., Slack/Telegram/Discord messages) and is injected into the agent’s LLM context via the agent node’stext: ={{ $json.chatInput }}/systemMessagetemplating.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata