speckle-syntax-webhooks

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md (see "Payload Structure" and "Webhook Integration Pattern") and examples (references/examples.md, e.g., Example 8/9) show the agent is expected to receive and parse external Speckle webhook POSTs and webhook.history payloads (user-generated/untrusted JSON fields like event.event_name, user, and payload) and to route/act on that data, so third‑party content can materially influence decisions and actions.