deploying-on-aws
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Prompt Injection (SAFE): No patterns of instruction override, safety filter bypass, or role-play injection were detected. The markdown files provide purely technical reference content.\n- Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network exfiltration commands were found. Examples in security.md use placeholders and standard AWS ARNs.\n- External Downloads (SAFE): The skill references 'aws-actions/configure-aws-credentials' in its GitHub Actions template. This is a repository owned by a trusted organization ('aws') and is standard for the intended deployment purpose.\n- Indirect Prompt Injection (SAFE): The skill defines a surface for processing user context to generate infrastructure code.\n
- Ingestion points: User requirements for generating the files defined in outputs.yaml.\n
- Boundary markers: None present in the schema definition.\n
- Capability inventory: Generates Terraform, Kubernetes manifests, and CI/CD workflows.\n
- Sanitization: Not explicitly defined within the skill files, but the provided blueprints are structurally defensive.\n- Privilege Escalation (SAFE): IAM policy examples and descriptions in the references folder strictly adhere to the principle of least privilege.
Audit Metadata