Ansible Playbook Template Library
Warn
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill's frontmatter includes a
verification: security_reviewedfield. This is a self-asserted claim that may mislead users into a false sense of security, as the claim is not independently verifiable within the skill's distribution context. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests external role and collection metadata from the Ansible Galaxy API and user requirements to generate executable code.
- Ingestion points: User-provided infrastructure requirements and role/collection metadata retrieved from the Ansible Galaxy API.
- Boundary markers: Absent. There are no instructions or delimiters defined to separate untrusted data from the agent's internal instructions.
- Capability inventory: The skill creates file structures and executes the
ansible-lintutility to process the generated content. - Sanitization: Absent. No mechanisms are described for validating or sanitizing data fetched from the external API before it is incorporated into generated playbooks.
- [COMMAND_EXECUTION]: The skill invokes the
ansible-lintCLI tool to perform validation on the generated Ansible playbooks.
Audit Metadata