implementing-soar-playbook-for-phishing

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs using the SOAR API token in the ph-auth-token HTTP header for API requests, which requires including a secret value verbatim in generated requests/commands and thus risks secret exfiltration.

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

• Third-party content exposure detected (high risk: 0.85). The skill ingests the phishing email’s headers/body (including extracted URLs/IPs) from a provided .eml file at runtime, and that email content is outsider-authored text (not written by the operating user), which is then converted into LLM-readable CEF artifact fields and used to trigger/prompt the SOAR playbook.