n8n

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user to paste their n8n API key into the conversation and to run a save command that includes the API key as a command-line argument, which requires the LLM to receive and could output the secret verbatim.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill queries a user-configurable n8n host (N8N_HOST set from ~/.config/n8n/host and validated in scripts/save_token.rb) and fetches JSON for workflows, executions, and workflow details via scripts like scripts/workflows.rb, scripts/workflow.rb, and scripts/executions.rb which the agent reads and uses to present and decide actions (including activating/deactivating workflows), so untrusted third-party content from arbitrary/public n8n instances could influence behavior.