Baoyu Danger Gemini Web

Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input,...

Security Scan

The skill's code and instructions match a reverse‑engineered Gemini Web client, but it accesses browser cookies / Chrome profiles and uses environment variables not declared in metadata — behavior that is sensitive and deserves explicit user consent and scrutiny.

Purpose & Capability

Name/description claim a reverse‑engineered Gemini Web client for text/image generation; included scripts implement that and call only Google/Gemini endpoints. Requiring browser session cookies and a Chrome debugging/CDP helper is coherent with the stated purpose (the client needs valid __Secure-1PSID / __Secure-1PSIDTS to authenticate).

Instruction Scope

SKILL.md and the shipped code instruct the agent to read/write consent and cookie files in user data directories, optionally load cookies from the local Chrome profile (using a bundled Chrome CDP module), launch or connect to Chrome debug ports, and write cached cookie files. These actions access sensitive local browser state (authentication cookies) and user config files beyond a simple API key — the SKILL.md does include an explicit consent flow, but the runtime instructions will read local browser cookies and may launch/manipulate Chrome sessions.

Install Mechanism

This is an instruction‑only skill (no external downloads at install time). Code is bundled in the skill (TypeScript + a vendored baoyu‑chrome‑cdp). It requires running the local scripts (bun or npx) but does not fetch arbitrary remote code during installation. No suspicious remote install URLs were found.

Credentials

Registry metadata declares no required env vars, but the code reads several environment variables (e.g., GEMINI_WEB_LOGIN, GEMINI_WEB_FORCE_LOGIN, GEMINI_WEB_CHROME_PROFILE_DIR, GEMINI_WEB_CHROME_PATH, BAOYU_CHROME_PROFILE_DIR and others) and will access local browser cookies and profile directories. Accessing browser cookies is equivalent to accessing authentication credentials — appropriate for this reverse‑engineered approach, but high‑sensitivity and not reflected in the required‑env metadata.

Persistence & Privilege

Skill does not request always:true and does not modify other skills. It will create/read/write cookie and consent files under user data dirs (e.g., ~/.local/share or %APPDATA%). It may launch or connect to Chrome via CDP, which is a privileged local action; this is powerful but consistent with its authentication strategy.

What to consider before installing

This skill implements a reverse‑engineered Gemini Web client that needs real Google session cookies to work. It will attempt to load cookies from your browser (via a bundled Chrome CDP helper), may launch or attach to Chrome, and will write cookie and consent files to your user data directories. Before installing: (1) Be sure you accept the SKILL.md consent flow; (2) prefer using a dedicated or disposable Chrome profile rather than your main browser profile if you proceed; (3) inspect the bundled code yourself (it’s included) or run it in an isolated environment; (4) be aware the skill can access sensitive cookies (equivalent to authentication credentials) and network to Google endpoints — revoke or rotate cookies if you later uninstall; (5) consider disabling autonomous invocation (or only invoke this skill manually) if you are uncomfortable with it accessing local browser state without an explicit prompt.

Gemini Web Client

Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations.

Script Directory

Important: All scripts are located in the scripts/ subdirectory of this skill.

Agent Execution Instructions:

1. Determine this SKILL.md file's directory path as {baseDir}
2. Script path = {baseDir}/scripts/<script-name>.ts
3. Resolve ${BUN_X} runtime: if bun installed → bun; if npx available → npx -y bun; else suggest installing bun
4. Replace all {baseDir} and ${BUN_X} in this document with actual values

Script Reference:

Script	Purpose
scripts/main.ts	CLI entry point for text/image generation
scripts/gemini-webapi/*	TypeScript port of gemini_webapi (GeminiClient, types, utils)

Consent Check (REQUIRED)

Before first use, verify user consent for reverse-engineered API usage.

Consent file locations:

• macOS: ~/Library/Application Support/baoyu-skills/gemini-web/consent.json
• Linux: ~/.local/share/baoyu-skills/gemini-web/consent.json
• Windows: %APPDATA%\baoyu-skills\gemini-web\consent.json

Flow:

1. Check if consent file exists with accepted: true and disclaimerVersion: "1.0"
2. If valid consent exists → print warning with acceptedAt date, proceed
3. If no consent → show disclaimer, ask user via AskUserQuestion:
   • "Yes, I accept" → create consent file with ISO timestamp, proceed
   • "No, I decline" → output decline message, stop
4. Consent file format: {"version":1,"accepted":true,"acceptedAt":"<ISO>","disclaimerVersion":"1.0"}

---

Preferences (EXTEND.md)

Check EXTEND.md existence (priority order):

# macOS, Linux, WSL, Git Bash
test -f .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md && echo "project"
test -f "${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md" && echo "xdg"
test -f "$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md" && echo "user"

# PowerShell (Windows)
if (Test-Path .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md) { "project" }
$xdg = if ($env:XDG_CONFIG_HOME) { $env:XDG_CONFIG_HOME } else { "$HOME/.config" }
if (Test-Path "$xdg/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md") { "xdg" }
if (Test-Path "$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md") { "user" }

┌──────────────────────────────────────────────────────────┬───────────────────┐ │ Path │ Location │ ├──────────────────────────────────────────────────────────┼───────────────────┤ │ .baoyu-skills/baoyu-danger-gemini-web/EXTEND.md │ Project directory │ ├──────────────────────────────────────────────────────────┼───────────────────┤ │ $HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md │ User home │ └──────────────────────────────────────────────────────────┴───────────────────┘

┌───────────┬───────────────────────────────────────────────────────────────────────────┐ │ Result │ Action │ ├───────────┼───────────────────────────────────────────────────────────────────────────┤ │ Found │ Read, parse, apply settings │ ├───────────┼───────────────────────────────────────────────────────────────────────────┤ │ Not found │ Use defaults │ └───────────┴───────────────────────────────────────────────────────────────────────────┘

EXTEND.md Supports: Default model | Proxy settings | Custom data directory

Usage

# Text generation
${BUN_X} {baseDir}/scripts/main.ts "Your prompt"
${BUN_X} {baseDir}/scripts/main.ts --prompt "Your prompt" --model gemini-3-flash

# Image generation
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cute cat" --image cat.png
${BUN_X} {baseDir}/scripts/main.ts --promptfiles system.md content.md --image out.png

# Vision input (reference images)
${BUN_X} {baseDir}/scripts/main.ts --prompt "Describe this" --reference image.png
${BUN_X} {baseDir}/scripts/main.ts --prompt "Create variation" --reference a.png --image out.png

# Multi-turn conversation
${BUN_X} {baseDir}/scripts/main.ts "Remember: 42" --sessionId session-abc
${BUN_X} {baseDir}/scripts/main.ts "What number?" --sessionId session-abc

# JSON output
${BUN_X} {baseDir}/scripts/main.ts "Hello" --json

Options

Option	Description
--prompt, -p	Prompt text
--promptfiles	Read prompt from files (concatenated)
--model, -m	Model: gemini-3-pro (default), gemini-3-flash, gemini-3-flash-thinking, gemini-3.1-pro-preview
--image [path]	Generate image (default: generated.png)
--reference, --ref	Reference images for vision input
--sessionId	Session ID for multi-turn conversation
--list-sessions	List saved sessions
--json	Output as JSON
--login	Refresh cookies, then exit
--cookie-path	Custom cookie file path
--profile-dir	Chrome profile directory

Models

Model	Description
gemini-3-pro	Default, latest 3.0 Pro
gemini-3-flash	Fast, lightweight 3.0 Flash
gemini-3-flash-thinking	3.0 Flash with thinking
gemini-3.1-pro-preview	3.1 Pro preview (empty header, auto-routed)

Authentication

First run opens browser for Google auth. Cookies cached automatically.

When no explicit profile dir is set, cookie refresh may reuse an already-running local Chrome/Chromium debugging session tied to a standard user-data dir. Set --profile-dir or GEMINI_WEB_CHROME_PROFILE_DIR to force a dedicated profile and skip existing-session reuse. This is a best-effort CDP session reuse path, not the Chrome DevTools MCP prompt-based --autoConnect flow described in Chrome's official docs.

Supported browsers (auto-detected): Chrome, Chrome Canary/Beta, Chromium, Edge.

Force refresh: --login flag. Override browser: GEMINI_WEB_CHROME_PATH env var.

Environment Variables

Variable	Description
GEMINI_WEB_DATA_DIR	Data directory
GEMINI_WEB_COOKIE_PATH	Cookie file path
GEMINI_WEB_CHROME_PROFILE_DIR	Chrome profile directory
GEMINI_WEB_CHROME_PATH	Chrome executable path
HTTP_PROXY, HTTPS_PROXY	Proxy for Google access (set inline with command)

Sessions

Session files stored in data directory under sessions/<id>.json.

Contains: id, metadata (Gemini chat state), messages array, timestamps.

Extension Support

Custom configurations via EXTEND.md. See Preferences section for paths and supported options.