gmail

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The workflow requires the agent to take the returned client-id and session-id (sensitive session tokens) and embed them verbatim into subsequent CLI commands/outputs, which forces the LLM to handle and output secret values.

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses Gmail API calls to read/retrieve email content (e.g., gmail_get_email, gmail_get_thread, gmail_list_emails), and that ingested message body/text is authored by external correspondents (outsider free text) rather than the operating user.