intercom

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt asks the user to paste their Intercom API access token and then shows running save_token.rb with the token embedded as a command-line argument ('PASTED_TOKEN'), which forces the agent to accept and/or output the secret verbatim.

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

• Third-party content exposure detected (high risk: 0.90). This skill fetches and displays user-generated content from the Intercom REST API (e.g., scripts/conversation.rb, conversations.rb, articles.rb, contacts.rb calling intercom_request against https://api.intercom.io), and those conversation/article bodies are read and used to drive replies and workflow decisions, so untrusted third-party content can indirectly inject instructions.