engineering-devops-automator
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection. Ingestion points: User-provided tasks via
scripts/run.sh. Boundary markers: No delimiters or ignore-instructions are defined in the instructions. Capability inventory: Role involves managing infrastructure via Terraform and Kubernetes. Sanitization: No sanitization logic or input validation is specified. - [EXTERNAL_DOWNLOADS]: The skill deliverables reference a Docker image from Secure Code Warrior, a well-known security technology company.
- [COMMAND_EXECUTION]: The execution script
scripts/run.shruns a python runner to process the skill instructions. - [SAFE]: No obfuscation, hardcoded credentials, or malicious persistence mechanisms were detected in the skill instructions or associated scripts.
Audit Metadata