senior-cloud-architect
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts including
scripts/cost_analyzer.py,scripts/dr_test.py,scripts/security_audit.py, andscripts/inventory.pyto automate architecture validation and operational tasks. - [EXTERNAL_DOWNLOADS]: The skill references a well-known community Terraform module (
terraform-aws-modules/vpc/aws) for infrastructure provisioning. - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection by ingesting and acting upon data from cloud environment scans and script outputs.
- Ingestion points: Output data generated by the cost analysis, disaster recovery, and security audit scripts mentioned in
SKILL.md. - Boundary markers: None identified; the instructions do not specify delimiters for data returned from cloud tools.
- Capability inventory: Local script execution and infrastructure modification capabilities via Terraform and cloud provider CLI tools.
- Sanitization: No explicit sanitization or validation logic is defined for processing the results of infrastructure scans.
Audit Metadata