kibana-connectors

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt contains concrete curl and config examples that place API keys, webhook URLs, and passwords directly into headers/bodies and kibana.yml, which means an agent generating runnable commands or configs would need to insert secret values verbatim—an explicit exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The workflows.md example includes an "enrich" ai.prompt step that calls an LLM connector (third‑party provider) and then uses steps.enrich.output in a subsequent create_case step, so untrusted LLM responses are ingested and can directly influence follow-up actions.