playbook-generator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected during the analysis of the skill's instructions and logic.
  • [COMMAND_EXECUTION]: The skill implements a strong security posture by explicitly forbidding the use of the ansible-playbook CLI and other local execution methods. It correctly delegates execution tasks to a separate, specialized skill (/playbook-executor), ensuring separation of concerns.
  • [PROMPT_INJECTION]: Instructions contain clear safety boundaries and do not exhibit any signs of behavior-override or safety-filter bypass patterns. The use of emphatic language (e.g., 'CRITICAL', '🚨') is strictly for enforcing operational safety.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local files or perform unauthorized network requests. All data processing is confined to legitimate MCP tool calls and CVE/system identifier handling.
  • [SAFE]: High-quality safety features are present, including a mandatory requirement for the user to review and approve the complete YAML playbook before it is returned, and a 'Return AS IS' policy that prevents the AI from making unauthorized modifications to generated code.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 06:04 PM