aws-solution-architect

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides AWS architecture patterns and infrastructure-as-code (IaC) generation logic. It facilitates standard cloud architecture workflows through local Python scripts and reference documentation. No evidence of malicious behavior, prompt injection, or credential exposure was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted application requirements and resource inventories from JSON files. However, it lacks autonomous execution capabilities; deployment commands are intended for user-led execution, providing a manual oversight checkpoint. Ingestion points include requirements.json, inventory.json, and current_setup.json. Capability inventory includes local file writes and generation of shell commands (aws-cli, cdk, terraform) for the user. Explicit boundary markers are absent, but basic string sanitization is performed on user-supplied application names in the serverless_stack.py script.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 02:33 PM
Security Audit — agent-trust-hub — aws-solution-architect