skills/awslabs/agent-plugins/deploy/Gen Agent Trust Hub

deploy

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill scans codebases to recommend AWS architectures. This represents a potential ingestion point for untrusted data.
  • Ingestion points: Codebase analysis mentioned in SKILL.md.
  • Boundary markers: The skill includes explicit instructions for pre-deployment secret detection and IaC security scanning in references/security.md.
  • Capability inventory: Generates and executes IaC code (CDK, Terraform, CloudFormation) via MCP servers.
  • Sanitization: Employs tools like cfn-nag, checkov, truffleHog, and detect-secrets to validate generated infrastructure and codebase safety before deployment.
  • [DYNAMIC_EXECUTION]: The skill generates infrastructure-as-code (IaC) scripts based on the codebase analysis and executes them following user confirmation.
  • Evidence: SKILL.md workflow steps 4 (Generate) and 5 (Deploy).
  • Context: The execution is gated by multiple security scans and explicit user approval, which is the standard intended functionality for a deployment skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 04:37 AM