senior-devops
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes local Python scripts (pipeline_generator.py, terraform_scaffolder.py, deployment_manager.py) and standard cloud CLI tools like terraform, aws, and kubectl to automate infrastructure tasks.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing untrusted user input such as file paths, container image tags, and environment names which are passed directly to automation scripts.
- Ingestion points: User-provided CLI arguments such as , , and --image in SKILL.md.
- Boundary markers: None identified; user input is interpolated directly into command structures without delimiters.
- Capability inventory: Comprehensive subprocess execution capabilities through management scripts and manual workflow commands.
- Sanitization: No explicit sanitization or validation of external input is described in the skill instructions or scripts descriptions.
Audit Metadata