Skills
Navigate
skills/elastic/agent-skills/security-case-management/Gen Agent Trust Hub

security-case-management

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the Kibana Cases API (titles, descriptions, comments) which could contain adversarial instructions.\n
  • Ingestion points: scripts/case-manager.js through API calls in the find, list, and get commands.\n
  • Boundary markers: Absent; tool output is reported verbatim per the skill instructions.\n
  • Capability inventory: Network communication with the user-configured KIBANA_URL via kibana-client.js.\n
  • Sanitization: Absent; the skill is instructed to report results exactly as returned by the API.\n- [COMMAND_EXECUTION]: The skill instructions include running npm install to manage Node.js dependencies in the skills/security directory. This is a standard setup procedure for this environment.\n- [SAFE]: The KIBANA_INSECURE environment variable allows the tool to bypass TLS certificate validation by setting NODE_TLS_REJECT_UNAUTHORIZED to '0'. This configuration is provided to support connections to clusters with self-signed certificates but represents a best-practice violation if used in untrusted networks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 07:35 AM
Security Audit — agent-trust-hub — security-case-management