ansible-generator

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute ansible-validator to verify generated project files as part of its deterministic execution flow in SKILL.md.
  • [COMMAND_EXECUTION]: The package includes a test script (test/test_fixture_regressions.py) that uses subprocess.run to execute ansible-playbook for verifying template and variable loading logic.
  • [PROMPT_INJECTION]: The skill processes user-supplied instructions to generate Ansible content, which constitutes a surface for Indirect Prompt Injection (Category 8).
  • Ingestion points: User requests for playbooks, roles, and tasks (SKILL.md).
  • Boundary markers: None defined within the generation workflow to isolate user input from the surrounding code templates.
  • Capability inventory: The skill performs file system writes (generating YAML/Jinja2 files) and command execution (running validation tools).
  • Sanitization: No explicit logic is provided to sanitize or escape user-provided strings before they are interpolated into the generated Ansible files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 06:18 PM