scaffold-typescript-frontend-quality-gates

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from the target repository, creating a surface for indirect prompt injection.
  • Ingestion points: Reads files such as AGENTS.md, package.json, and various configuration files to analyze the existing project state.
  • Boundary markers: The instructions do not define specific boundary markers for the ingested data.
  • Capability inventory: The skill can propose file modifications and execute local scripts (e.g., run_gates.sh or npm run lint) to verify the setup.
  • Sanitization: The skill includes a robust mitigation via the confirmation-before-write gate, which requires explicit human approval before the agent takes any action or executes code.
  • [COMMAND_EXECUTION]: The skill involves running local scripts as part of the quality gate verification process. This functionality is intended for the skill's primary purpose and is protected by a manual confirmation step.
  • [EXTERNAL_DOWNLOADS]: The skill references documentation and official repositories for established technology services including Biome, ESLint, TypeScript, and Vitest. These are verified sources within the technology ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 03:02 AM
Security Audit — agent-trust-hub — scaffold-typescript-frontend-quality-gates