n8n

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt embeds plaintext credentials (e.g., N8N_BASIC_AUTH_PASSWORD, DB_POSTGRESDB_PASSWORD, POSTGRES_PASSWORD) in example config, which the LLM would likely reproduce verbatim when returning the snippet or instructions, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly ingests external webhook payloads and third-party integration data (see "Step 2: Webhook Trigger" and the API workflow/Code node in "Step 3"/"Step 4"), which are untrusted user-generated inputs that the automation reads and uses to drive decisions and downstream actions.