aws-cdk-development

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface.\n
  • Ingestion points: The skill retrieves external data using AWS MCP tools (mcp__aws-mcp__aws___search_documentation, mcp__aws-mcp__aws___read_documentation) as specified in SKILL.md.\n
  • Boundary markers: No explicit instructions or delimiters are used to prevent the agent from following malicious instructions potentially embedded in the retrieved documentation.\n
  • Capability inventory: The skill includes a validation script (scripts/validate-stack.sh) that executes cdk synth, which performs code synthesis and could be influenced by malicious patterns ingested during the design phase.\n
  • Sanitization: There is no evidence of filtering or validation of content retrieved from the external AWS documentation sources.\n- [COMMAND_EXECUTION]: Local Script Execution.\n
  • The scripts/validate-stack.sh script executes the cdk CLI (cdk synth) and utilizes system tools like grep, find, and jq to inspect the project structure and synthesized templates. This is a standard part of the CDK development workflow but represents a local command execution capability.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 02:23 AM