Baoyu Danger Gemini WebSAFE
Overview
An agent skill published by jimliu.
ae9966d431c4OBSERVED · 2026-10-24Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| openclaw | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: baoyu-danger-gemini-web
description: Generates images and text via reverse-engineered Gemini Web API. Supports text generation, image generation from prompts, reference images for vision input, and multi-turn conversations. Use when other skills need image generation backend, or when user requests "generate image with Gemini", "Gemini text generation", or needs vision-capable AI generation.
version: 1.56.2
metadata:
openclaw:
homepage: https://github.com/JimLiu/baoyu-skills#baoyu-danger-gemini-web
requires:
anyBins:
- bun
- npx
---
# Gemini Web Client
Text/image generation via Gemini Web API. Supports reference images and multi-turn conversations.
## User Input Tools
When this skill prompts the user, follow this tool-selection rule (priority order):
1. **Prefer built-in user-input tools** exposed by the current agent runtime — e.g., `AskUserQuestion`, `request_user_input`, `clarify`, `ask_user`, or any equivalent.
2. **Fallback**: if no such tool exists, emit a numbered plain-text message and ask the user to reply with the chosen number/answer for each question.
3. **Batching**: if the tool supports multiple questions per call, combine all applicable questions into a single call; if only single-question, ask them one at a time in priority order.
Concrete `AskUserQuestion` references below are examples — substitute the local equivalent in other runtimes.
## 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 in priority order — the first one found wins:
| Priority | Path | Scope |
|----------|------|-------|
| 1 | `.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | Project |
| 2 | `${XDG_CONFIG_HOME:-$HOME/.config}/baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | XDG |
| 3 | `$HOME/.baoyu-skills/baoyu-danger-gemini-web/EXTEND.md` | User home |
If none found, use defaults.
**EXTEND.md supports**: Default model, proxy settings, custom data directory.
## Usage
```bash
# 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` | CTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
baoyu-chrome-cdp
Gates applied: no_behavioural_pass.
ae9966d431c4full audit observations/trust-audit/skill/jimliu__baoyu-danger-gemini-web.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-24 | ae9966d431c4 | SAFE | B | 89 | first audit |
Questions
Is baoyu-danger-gemini-web — jimliu/baoyu-skills safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can baoyu-danger-gemini-web — jimliu/baoyu-skills access on my machine?
The audit observed that it reaches the network and runs shell commands. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does baoyu-danger-gemini-web — jimliu/baoyu-skills work with?
Its documentation mentions openclaw. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (ae9966d431c4), read on 2026-10-24. The repository is watched, and a new audit runs when it changes — this is the first audit.
Add this badge to your README
Shows this page's audit result and links back to it. It updates when the audit does.
[](https://modelsatlas.com/skills/jimliu/baoyu-danger-gemini-web/)
Not your listing, or something out of date? Claim or update your listing.