mobile app builder with live link, publishes to app store, create ai apps

Build full-stack web and mobile apps from a text description. Creates projects, plans features, and starts Quick Start builds for background execution.

This skill appears to implement what it claims (building, iterating, and publishing apps), but it will: (1) start a device-login flow or accept personal tokens and then save a PAT to ~/.openclaw/launchpulse/auth.json (or a custom OPENCLAW_STATE_DIR), (2) accept many optional external-service tokens (GitHub, Fly, Stripe, RevenueCat) necessary for deployment/publishing, and (3) send project data to a hosted API (api.launchpulse.ai by default). Before installing or using it: inspect the included script, confirm the API base URL is legitimate, avoid entering high-privilege production secrets unless necessary (use least-privilege or temporary tokens), consider setting OPENCLAW_STATE_DIR to a controlled location, and delete local auth.json when done. If you need higher assurance, run the skill in a sandboxed environment or review network traffic to verify what data is sent.

Type: OpenClaw Skill Name: mobile-app-builder-ai Version: 1.0.0 The skill is classified as suspicious due to multiple critical vulnerabilities. The `SKILL.md` instructions pose a prompt injection risk, as they direct the OpenClaw agent to execute `node` commands with user-controlled input (e.g., `<description>`, `<change request>`) directly interpolated, potentially leading to shell injection against the agent's host. Additionally, the `scripts/launchpulse.cjs` script contains a Local File Inclusion (LFI) vulnerability, where user-supplied file paths for `--payload-file`, `--vars-file`, and `--contact-file` are read directly using `fs.readFileSync`, allowing arbitrary file access on the agent's system. The `db query` command also passes raw user SQL to the backend API, creating a potential SQL injection vulnerability in the overall system. While these are severe flaws, there is no clear evidence of intentional malicious behavior (e.g., exfiltration to an attacker-controlled domain, persistence mechanisms) within the provided files, indicating they are likely vulnerabilities rather than deliberate malware.