dev

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local development binaries such as portless, emulate, and agent-browser. It prevents command injection by sanitizing git branch names into DNS-safe slugs using character stripping and truncation before using them as command arguments.
  • [EXTERNAL_DOWNLOADS]: Refers to standard development packages and system utilities. Installation recommendations point to official registries like NPM and Homebrew. It uses npx wait-on for health checks, which is a common and trusted development utility.
  • [DATA_EXFILTRATION]: Contains a documented feature to expose local servers to the internet using Tailscale Funnel. This functionality is user-triggered via specific flags and is accompanied by a explicit warning that the service will be public on the internet.
  • [SAFE]: Implements defensive programming techniques including atomic file writes for state management, localized storage within the project's .claude directory, and clean process termination using recursive tree walking.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 01:09 AM
Security Audit — agent-trust-hub — dev