n8n-workflow-creator
Warn
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
node -eto perform API operations. This allows for dynamic execution of JavaScript strings which include variable parameters like workflow IDs and API keys. - [EXTERNAL_DOWNLOADS]: The skill makes repeated network requests to a specific third-party domain (
n8n.srv1123427.hstgr.cloud) that is not recognized as a well-known or trusted service. This domain acts as the hub for all workflow management operations. - [PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection. It ingests data from external API responses (workflow definitions and execution logs) and processes them without visible sanitization or boundary markers.
- Ingestion points: Workflow list and execution log endpoints in
SKILL.md. - Boundary markers: Absent; data is logged directly to the console.
- Capability inventory: Shell command execution via
node -eis available across all core commands. - Sanitization: None detected in the provided implementation examples.
Audit Metadata