frontend-playbook

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to run multiple CLI tools, including yarn, npx, cast, and curl, to perform tasks such as project setup, contract deployment, and interacting with the Vercel API.
  • [DYNAMIC_EXECUTION]: The instructions direct the agent to generate a specific JavaScript polyfill (polyfill-localstorage.cjs) from a provided template and execute it during the Next.js build process by setting the NODE_OPTIONS environment variable.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies ingestion points for untrusted data, specifically when asking the user for a desired ENS subdomain and for project feedback during the production checklist. This data is intended to be used in build commands and environment variables; however, the skill lacks boundary markers or sanitization instructions to prevent this input from being used to inject malicious instructions.
  • [EXTERNAL_DOWNLOADS]: The playbook utilizes npx create-eth@latest to bootstrap projects, which involves downloading and executing the latest scaffolding code from the public npm registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 05:34 AM