airwallex-webhooks

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow for the webhook handlers ingests outsider-authored free text (the HTTP request body and headers like x-timestamp/x-signature) directly from external senders, parses it into JSON, and uses it in control flow, so the LLM context would be exposed if any LLM generation/summarization step were later added on these fields.