sanity-webhooks

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

• Third-party content exposure detected (high risk: 0.85). The skill’s required runtime path is receiving HTTP webhook payloads from Sanity (outsider-authored free text: the JSON body and fields like _type, _id, etc.) via req.body/rawBody and parsing it (JSON.parse(rawBody)), which would then be available in the agent/handler for any LLM context construction.