n8n-agents-official
Warn
Audited by Snyk on Jul 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md describes an n8n Agent whose runtime input is the chat/webhook text (e.g.,
text: '={{ $json.userMessage }}'), which is outsider-authored free text from external chat surfaces; that text becomes part of the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata