cloud-architect
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access mechanisms were detected in the instructions or metadata. The skill follows best practices for the domain.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection based on its intended functionality.
- Ingestion points: The skill processes external user-supplied architectural requirements and references a local resource file,
resources/implementation-playbook.md. - Boundary markers: There are no instructions or delimiters provided to ensure the agent ignores instructions that may be embedded within these external inputs.
- Capability inventory: The skill is capable of generating Infrastructure as Code (Terraform, CDK) and recommends executing security and infrastructure testing tools (Checkov, Terrascan, Terratest).
- Sanitization: The skill does not include logic for sanitizing or validating requirements before they are incorporated into architectural designs or code generation.
Audit Metadata