cloud-best-practices
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructs the agent to follow industry-standard security baselines, including multi-factor authentication, least-privilege IAM roles, encryption at rest and in transit, and robust secrets management. It correctly identifies the shared responsibility model between cloud providers and customers.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied cloud architecture details and compliance goals to generate security mappings and code. 1. Ingestion points: User descriptions of cloud workloads and specific compliance requirements (SKILL.md). 2. Boundary markers: Not explicitly defined in the instructions to isolate user input from the reasoning logic. 3. Capability inventory: Generates Infrastructure-as-Code templates (Terraform, CloudFormation, Bicep) and provides guidance on CI/CD policy gating. 4. Sanitization: No specific input validation or escaping mechanisms are described; the skill relies on the agent's internal safety filters.
Audit Metadata