n8n-gen
Warn
Audited by Snyk on Mar 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: 0.90). The SKILL.md explicitly instructs the agent to use Playwright to scrape and copy JSON templates from the public site https://n8n.io/workflows into n8n_references and then read those downloaded templates to synthesize final workflows, so publicly-hosted third-party content can directly influence the agent's design and actions.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill uses Playwright at runtime to scrape and download JSON templates from https://n8n.io/workflows/, and those external templates are read and injected into the agent's synthesis process as required references that directly influence the generated prompts/instructions.
Audit Metadata