sumsub-manage-webhooks

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

• Third-party content exposure detected (high risk: 0.75). The skill’s get/list runtime path calls Sumsub’s public API (GET /resources/clientWebhooks and GET /resources/clientWebhooks/{id}) and ingests the returned webhook JSON (including secretKey before client-side redaction) into the agent’s context; this is outsider-authored content from Sumsub’s tenant data, not authored by the operating user.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)