iblai-api-agent-support

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

• Third-party content exposure detected (high risk: 0.75). This skill’s runtime workflow includes reading outsider-authored ticket/reply text via the authenticated API GET endpoints for support-tickets/{id}/ and support-ticket-messages/ (ticket description and message come from end users/agent chat escalations, not the operating user), which the agent would then place into the LLM context for triage/response.