n8n
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from the n8n API which could contain malicious instructions. 1. Ingestion points: Workflow names, node names, and error messages are fetched from the API in workflow.rb, execution.rb, and workflows.rb. 2. Boundary markers: No delimiters or ignore instructions are used when presenting API data to the agent context. 3. Capability inventory: The skill performs network operations (n8n_request) across all scripts and modifies state in activate.rb and deactivate.rb. 4. Sanitization: API response data is displayed directly without escaping or validation.
- [DATA_EXPOSURE]: The skill stores API keys in ~/.config/n8n/api_key. While it sets restrictive file permissions (0600) in save_token.rb, the key is passed as a command-line argument during setup, making it potentially visible in process lists and shell history.
Audit Metadata