create-deploy-strategy
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill's core functionality involves ingesting user-provided data, such as health check endpoints and rollback criteria, and interpolating it into generated deployment configurations. This creates a surface for indirect prompt injection where malicious input could alter the behavior of the generated scripts. * Ingestion points: User-provided parameters defined in the 'Usage' section of 'SKILL.md'. * Boundary markers: None are present to separate untrusted user data from the generated script logic. * Capability inventory: The skill generates executable configurations including GitHub Actions workflows, GitLab CI scripts, and PHP health check code. * Sanitization: The instructions do not specify any sanitization or validation steps for the user-provided inputs.
- [COMMAND_EXECUTION]: The templates provided in the skill generate scripts that perform shell command execution and remote system access. * Evidence: The CI/CD workflows in 'SKILL.md' and 'references/templates.md' utilize commands such as 'ssh', 'docker', 'kubectl', and 'curl' to manage deployments and traffic switching.
Audit Metadata