skills/delorenj/skills/aws-blocks/Gen Agent Trust Hub

aws-blocks

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill triggers on external project data, which is a potential surface for indirect injection.
  • Ingestion points: The skill activates when it detects an aws-blocks/ directory or @aws-blocks imports in the user's codebase.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands in project files are present.
  • Capability inventory: The skill uses shell commands (npx, npm) to interact with the environment.
  • Sanitization: The skill does not describe specific sanitization for data ingested from the project files.
  • [COMMAND_EXECUTION]: The instructions guide the user to execute shell commands for scaffolding (npx @aws-blocks/create-blocks-app), local testing (npm run sandbox), and deployment (npm run deploy).
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests the execution of packages from the @aws-blocks NPM scope, which are external dependencies necessary for the framework's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — aws-blocks