webhook-processor

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

• Third-party content exposure detected (high risk: 0.90). The skill’s scaffold and overview explicitly accept and process incoming webhooks from external senders (e.g., “payment providers, version control platforms, or third-party APIs” in SKILL.md and the /webhooks/:source endpoint), meaning untrusted, user-generated payloads are parsed and used to route actions (e.g., triggering builds), which could allow indirect instruction injection.