kibana-cases
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from investigation and incident cases that could contain malicious instructions.
- Ingestion points: The skill ingests case metadata, titles, descriptions, and user-provided comments via the
GET /api/cases/_findandGET /api/cases/{caseId}/comments/_findendpoints (SKILL.md). - Boundary markers: The instructions lack requirements for using boundary markers or delimiters when presenting case content to the agent or incorporating it into secondary actions.
- Capability inventory: The agent has extensive write capabilities, including creating, updating, and deleting cases, as well as executing commands through the
elasticCLI (SKILL.md). - Sanitization: No evidence was found of sanitization or filtering logic applied to external case content before it is processed by the agent.
Audit Metadata