Skills
skills/julianobarbosa/claude-code-skills/zabbix/Gen Agent Trust Hub

zabbix

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE] (LOW): Hardcoded default credentials (Admin/zabbix) are present in documentation examples in SKILL.md and references/api-reference.md. While these are Zabbix defaults, users should follow the skill's own best practices to use environment variables or API tokens instead.
  • [PROMPT_INJECTION] (LOW): The skill processes external data from CSV and JSON files to manage Zabbix objects without sanitization, creating an indirect prompt injection surface.
  • Ingestion points: scripts/zabbix-bulk-hosts.py (CSV ingestion) and scripts/zabbix-export.py (JSON ingestion).
  • Boundary markers: Absent; data from files is directly passed to the API parameters.
  • Capability inventory: The skill can create, update, and delete hosts, templates, triggers, and users via zabbix_utils.ZabbixAPI.
  • Sanitization: No validation or escaping is performed on input data before being sent to the Zabbix API.
  • [EXTERNAL_DOWNLOADS] (SAFE): Recommends the installation of the official zabbix-utils package from PyPI.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:37 PM