modify-cdk-workflows

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the agent to perform local verification of CDK infrastructure changes using the command cd cdk && npx cdk synth.
  • [COMMAND_EXECUTION]: After verification, the skill instructs the agent to trigger a deployment using the custom tool command /deploy-cdk-stack.
  • [PRIVILEGE_ESCALATION]: The file references/CDK-PATTERNS.md provides an example IAM policy that grants the bedrock:InvokeModel action to all resources (*). While common in development samples, this represents a broad permission configuration that does not adhere to the principle of least privilege.
  • [INDIRECT_PROMPT_INJECTION]: This skill presents an attack surface for indirect prompt injection because it modifies existing project source code. • Ingestion points: The agent reads and modifies review-processor.ts, checklist-processor.ts, and parameter-schema.ts. • Boundary markers: No explicit delimiters or instructions to ignore embedded code comments are provided. • Capability inventory: The agent has the capability to run cdk synth and execute deployment commands via /deploy-cdk-stack. • Sanitization: No specific sanitization or validation of the existing code content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 01:38 AM