Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Third-party content exposure detected (high risk: 0.90). The skill launches an AI-controlled headed browser and explicitly issues browse commands and sidebar-agent actions that read and act on live public web pages (e.g., Step 4's $B goto https://news.ycombinator.com demo and Step 5's sidebar chat "take a snapshot and describe this page"), so it ingests untrusted third‑party/web (user-generated) content that can influence subsequent actions.
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Potentially malicious external URL detected (high risk: 1.00). During runtime setup the skill downloads and executes a remote install script via curl from https://bun.sh/install (saved to a temp file and run with bash), which fetches and runs remote code as a required setup dependency.
db9447c
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.