coreeb-fullstack

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The instructions mandate that the agent must automatically install specific Node.js packages (pnpm add coreeb sonner tw-animate-css axios) if they are missing from the package.json file. This represents an automated shell execution pattern.
  • [CREDENTIALS_UNSAFE]: The provided template for the .env file and DATABASE_URL contains hardcoded placeholder credentials (postgres:postgres). While intended for local development environments, these patterns should be replaced with secure secrets in production contexts.
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by design. It performs file system operations (creating modular structures) and package management based on instructions that could be influenced by external project data (like an existing package.json).
  • Ingestion points: Reading and reviewing the package.json file in the root directory (SKILL.md).
  • Boundary markers: None identified.
  • Capability inventory: File writing (creating modules/components), shell execution (pnpm, docker compose, prisma), and network requests (via generated Axios client).
  • Sanitization: No explicit sanitization or validation of the ingested package.json content before determining installation actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:32 PM