ansible
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill makes extensive use of command and shell execution modules which are central to its purpose of server configuration and management. It mitigates risks by mandating the use of attributes like changed_when to ensure idempotency.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to process and review playbooks, roles, and inventories, there is an inherent attack surface for indirect prompt injection from untrusted configuration data.
- Ingestion points: Playbooks, roles, and inventories (SKILL.md).
- Boundary markers: Includes an AI Self-Check and a Production Checklist to verify generated content (SKILL.md, references/production-checklist.md).
- Capability inventory: Access to system modules like apt, shell, command, uri, and file (references/playbook-patterns.md).
- Sanitization: Explicitly requires no_log: true for all secret-handling tasks and enforces the use of Ansible Vault for encryption (references/vault-and-secrets.md).
- [DYNAMIC_EXECUTION]: Provides documentation patterns for executing Python scripts via shell heredocs to audit AWX activity streams (references/compliance.md).
- [EXTERNAL_DOWNLOADS]: Describes the installation of Ansible collections and roles from external registries like Ansible Galaxy. The skill warns about the lack of hash verification and the risks of supply chain attacks (SKILL.md, references/roles-and-collections.md).
Audit Metadata