Live survey304 models · 14 providers · 23,592 auditsAudited implement · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

baoyu-skills

skill · JimLiu/baoyu-skillsMIT licenceAudited 12 Nov 2026 · source e63a35febc0c

★ 27,495pushed 6 days agoversion 1.1.0
✕BLOCKGrade F · 48/100 · 25 findings · e63a35f
27,495repo stars · whole JimLiu/baoyu-skills

Is it safe? No — BLOCK, grade F (48/100). We read this skill's source at commit e63a35febc0c and observed filesystem, network and shell access and no hard-coded secrets. The audit raised 25 findings, 4 critical or high. What it does: Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “baoyu-skills (JimLiu/baoyu-skills)”. Retrieved 12 Nov 2026. https://modelsatlas.com/skills/jimliu/baoyu-skills

Blocked. The page stays public so you can check this skill if someone recommended it to you. The audit found 4 critical or high findings, starting with “Prompt injection” in skills/baoyu-post-to-wechat/SKILL.md:162. Do not install it without reading them.

2 skills are called “baoyu-skills”. You are viewing JimLiu/baoyu-skills. 2 of them are BLOCK.

Trust audit

Audit 0.4.1 · source read 12 Nov 2026

Trust score48/100✕BLOCK F
1 critical3 high1 medium26 low4 info

BLOCK means the audit found something that could harm you or your machine. Grade F is shared by 129 of 18,389 audited skills.

What the source does

  • FilesystemDeclared5 observations
  • NetworkDeclared5 observations
  • ShellDeclared7 observations
  • DependenciesNot pinnedSome versions float
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN2
L1 Static sourceSecrets, path traversal, supply chain, hidden codeFAIL21
L2 InstructionsPrompt injection, authority framing, hidden directivesFAIL2
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: critical finding, no behavioural pass, undeclared transfer.

Findings (25)

CRITICALPrompt injectionprompt.transfer_instruction · skills/baoyu-post-to-wechat/SKILL.md:162
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
**`remote-api`**: for when "公众号设置 → IP 白名单" excludes the local IP but includes a server's. Rendering, image processing, draft assembly and HTML rewriting stay local; only the HTTPS calls to `api.weixi
Why
an instruction to move sensitive data to an outside destination
Fix
remove; a skill never needs the user's secrets off the machine
HIGHCode injectioncode.eval_exec · packages/baoyu-md/src/html-builder.ts:9
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
const value = eval(
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHCode injectioncode.eval_exec · packages/baoyu-md/src/themes.ts:8
F-02 Code injectionCWE-78 · CWE-94 · CWE-95Layer L1
const value = eval(
Why
evaluates text as code
Fix
remove; use a parser or a dispatch table
HIGHPrompt injectionprompt.credential_read · skills/baoyu-post-to-wechat/SKILL.md:244
F-01 Prompt injectionCWE-94 · CWE-1427Layer L2
| Access token error | Verify credentials valid and not expired |
Why
asks the agent to read credentials
Fix
—
MEDIUMInventory / provenanceinv.binary · bun.lockb
F-13 Inventory / provenanceCWE-1104Layer L0
bun.lockb
Why
a compiled or binary member cannot be reviewed from source
Fix
ship source, or explain the binary in the README
LOWInventory / provenanceinv.hidden_file · .releaserc.yml
F-13 Inventory / provenanceCWE-1104Layer L0
.releaserc.yml
Why
hidden member outside the usual dotfiles
Fix
review its purpose
LOWInsecure cryptocrypto.weak_hash · packages/baoyu-md/src/images.ts:118
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
const hash = createHash("md5").update(imagePath).digest("hex").slice(0, 8);
Why
No further detail recorded for this rule.
Fix
—
LOWInsecure cryptocrypto.weak_hash · skills/baoyu-electron-extract/scripts/main.ts:508
F-09 Insecure cryptoCWE-327 · CWE-338Layer L1
const h = createHash("sha1").update(src).digest("hex").slice(0, 10);
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.credential_store · skills/baoyu-post-to-wechat/scripts/wechat-extend-config.test.ts:163
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
"remote_publish_identity_file: /home/me/.ssh/id_ed25519",
Why
touches a credential store
Fix
—
LOWFilesystem / pathfs.credential_store · skills/baoyu-post-to-wechat/scripts/wechat-extend-config.test.ts:164
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
"remote_publish_known_hosts_file: /home/me/.ssh/known_hosts",
Why
touches a credential store
Fix
—
LOWFilesystem / pathfs.credential_store · skills/baoyu-post-to-wechat/scripts/wechat-extend-config.test.ts:178
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
assert.equal(resolved.remote_publish_identity_file, "/home/me/.ssh/id_ed25519");
Why
touches a credential store
Fix
—
LOWFilesystem / pathfs.credential_store · skills/baoyu-post-to-wechat/scripts/wechat-extend-config.test.ts:179
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
assert.equal(resolved.remote_publish_known_hosts_file, "/home/me/.ssh/known_hosts");
Why
touches a credential store
Fix
—
LOWFilesystem / pathfs.credential_store · skills/baoyu-post-to-wechat/scripts/wechat-remote-publish.test.ts:39
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
identityFile: "/home/me/.ssh/id_ed25519",
Why
touches a credential store
Fix
—
LOWFilesystem / pathfs.traversal · packages/baoyu-fetch/src/adapters/generic/index.ts:2
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { detectInteractionGate } from "../../browser/interaction-gates";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · packages/baoyu-fetch/src/adapters/generic/index.ts:3
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { captureNormalizedPageSnapshot } from "../../browser/page-snapshot";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · packages/baoyu-fetch/src/adapters/generic/index.ts:4
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { convertHtmlToMarkdown } from "../../extract/html-to-markdown";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · packages/baoyu-fetch/src/adapters/hn/index.ts:5
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import type { ExtractedDocument } from "../../extract/document";
Why
No further detail recorded for this rule.
Fix
—
LOWFilesystem / pathfs.traversal · packages/baoyu-fetch/src/adapters/hn/index.ts:6
F-05 Filesystem / pathCWE-22 · CWE-59Layer L1
import { collectMediaFromDocument } from "../../media/markdown-media";
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · README.md:1376
F-04 Network egressCWE-200 · CWE-319Layer L1
HTTP_PROXY=http://127.0.0.1:7890 HTTPS_PROXY=http://127.0.0.1:7890 /baoyu-danger-gemini-web "Hello"
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · README.md:1382
F-04 Network egressCWE-200 · CWE-319Layer L1
$env:HTTP_PROXY = 'http://127.0.0.1:7890'
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · README.md:1383
F-04 Network egressCWE-200 · CWE-319Layer L1
$env:HTTPS_PROXY = 'http://127.0.0.1:7890'
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · README.zh.md:1377
F-04 Network egressCWE-200 · CWE-319Layer L1
HTTP_PROXY=http://127.0.0.1:7890 HTTPS_PROXY=http://127.0.0.1:7890 /baoyu-danger-gemini-web "你好"
Why
No further detail recorded for this rule.
Fix
—
LOWNetwork egressnet.raw_ip · README.zh.md:1383
F-04 Network egressCWE-200 · CWE-319Layer L1
$env:HTTP_PROXY = 'http://127.0.0.1:7890'
Why
No further detail recorded for this rule.
Fix
—
LOWSupply chainsupply.unpinned · package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
pdf-lib, pptxgenjs, sharp, @mozilla/readability, linkedom, turndown, turndown-plugin-gfm, tsx
Why
8 dependency range(s) float
Fix
pin exact versions or ship a lockfile
LOWSupply chainsupply.unpinned · packages/baoyu-fetch/package.json
F-08 Supply chainCWE-829 · CWE-1357Layer L1
@mozilla/readability, chrome-launcher, defuddle, jsdom, remark-gfm, remark-parse, turndown, turndown-plugin-gfm
Why
15 dependency range(s) float
Fix
pin exact versions or ship a lockfile

Audit 0.4.1 · source sha e63a35febc0c · 12 Nov 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • PublisherJimLiu GitHub userOwner of the repository this skill is read from
  • Source folderJimLiu/baoyu-skillsThe exact folder we audited
  • LicenceMITAs the repository states it
  • Commit pinned for this verdicte63a35febc0cA new audit runs when the source changes
  • Repository statusNot archivedLast push 6 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate…

---
name: baoyu-article-illustrator
description: Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style × Palette three-dimension approach. Use when user asks to "illustrate article", "add images", "generate images for article", or "为文章配图".
version: 1.117.4
metadata:
  openclaw:
    homepage: https://github.com/JimLiu/baoyu-skills#baoyu-article-illustrator
---

# Article Illustrator

## 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.

## Image Generation Tools

Resolve the image backend in this order:

1. **User names a backend** in the current message → use it.
2. **`preferred_image_backend`** in `EXTEND.md` names a backend available now → use it. `ask` means ask every run.
3. **Auto-select** (preference `auto`, unset, or the pinned backend is unavailable), first match wins:
   - **Codex `imagegen`** skill is in your available skills → you are in Codex and MUST use it: `Skill` with `skill: "imagegen"`, passing the prompt file's content plus output path and aspect ratio. It outranks non-native skills such as `baoyu-image-gen`.
   - **Codex via `codex exec` (`codex-imagegen`)**: no native `imagegen`, but the `codex` CLI is on `PATH` with an active `codex login` → `baoyu-image-gen --provider codex-cli` (preferred), or the bundled wrapper if baoyu-image-gen is unavailable. Load [references/codex-imagegen.md](references/codex-imagegen.md) only for this branch.
   - **Cursor `GenerateImage`** → use it (outranks non-native skills). It has no aspect-ratio parameter, so state the aspect ratio / dimensions in the `description` prompt; it saves to a tool-managed location, so copy the file to the expected output path (e.g., `outputs/.../NN-xxx.png`). Reference images go in `reference_image_paths`.
   - **Other runtime-native image tool** (e.g., Hermes `image_generate`) → use it the same way.
   - Exactly one non-native backend installed (e.g., `baoyu-image-gen`) → use it.
   - Several non-native backends → ask the user once, batched with other initial questions.
4. **None available** → tell the user and ask how to proceed.

**⛔ Raster only**: never substitute SVG, HTML/CSS, canvas, or other code-based rendering for a raster image, even for diagram-like content. If no raster backend resolves, go to step 4.

**⛔ No bitmap text patching**: never use ImageMagick, Pillow, Canvas, SVG, HTML/CSS, OCR scripts, or any other overlay to cover, rewrite, erase, stroke, or replace labels, captions, or any other text inside an already generated illustration. Regenerate from a corrected prompt, redraw with less or no on-image text, or ask the user which imperfect candidate to keep.

**Prompt file (hard)**: before invoking any backend, write each image's full, final prompt to its own file under `prompts/` (`NN-{type}-[slug].md`) and pass that file (or its content) to the backend. It is the reproducibility record and lets you switch backends without rewriting prompts.

Change the pinned backend via `## Changing Preferences` below. Tool names above are examples; use the local equivalent in other runtimes.

## Batch Generation Policy

After every prompt file for the run has been saved and verified, generate images in batches by default:

1. Use the chosen backend's native batch / multi-task interface if it exists. Each task keeps its own prompt file, output path, aspect ratio, and direct reference images.
2. Otherwise, if the runtime can issue parallel tool calls, dispatch up to `generation_batch_size` images at a time (default `4`). An explicit request in the current message (`--batch-size 4`, "并行4张一起生成") overrides EXTEND.md.
3. Otherwise generate sequentially.

- Never start a batch until all its prompt files exist on disk.
- Retry failed items once without regenerating successful ones.
- Don't use subagents just to parallelize rendering; only for separate per-image prompt iteration or creative exploration.

## Confirmation Policy

Default: **confirm before generation**.

- Explicit skill invocation, a file path, matched signals/presets, and `EXTEND.md` defaults are recommendation inputs only — none authorizes skipping confirmation.
- Do not start Step 4 or later until the user completes Step 3.
- Skip confirmation only when the current request explicitly says so ("直接生成", "不用确认", "跳过确认", "按默认出图", or equivalent). Then state the assumed type / density / style / palette / language / backend in the next user-facing update before generating.

## Reference Images

Users may supply refs via `--ref <files...>`, file paths, or pasted images; they guide style, palette, composition, or subject. Step 1.0 in [references/workflow.md](references/workflow.md) saves them to `references/NN-ref-{slug}.{ext}`; Step 5.3 processes per-illustration usage `direct | style | palette`. When the backend supports batch input, propagate `direct` entries from each prompt file's `references:` frontmatter into its batch task (e.g. `baoyu-image-gen` accepts `ref` per task).

## Three Dimensions

| Dimension | Controls | Values |
|-----------|----------|--------|
| **Type** | Information structure | `infographic` (data, metrics, technical), `scene` (narrative, emotional), `flowchart` (processes), `comparison` (side-by-side), `framework` (models, architecture), `timeline` (history, evolution) |
| **Style** | Rendering approach | See [

Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit e63a35f

npx skills add jimliu/baoyu-skills
npx skills add JimLiu/baoyu-design
npm install -g @openai/codex

Commands as the repository documents them: shown, never run by us. Our verdict covers commit e63a35febc0c only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
Claude CodeMentioned in its text, not testedSkills for Claude Code · About Claude Code
Claude DesktopMentioned in its text, not testedSkills for Claude Desktop · About Claude Desktop
CodexMentioned in its text, not testedSkills for Codex · About Codex
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
OpenClawMentioned in its text, not testedSkills for OpenClaw · About OpenClaw
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. ✕BLOCK F 48 / 100

    first audit · source e63a35febc0c

README badge

For maintainers · shows the latest audit

ModelsAtlas: BLOCK FMODELSATLASBLOCK · F
[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/jimliu/baoyu-skills/badge.svg)](https://modelsatlas.com/skills/jimliu/baoyu-skills/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

Similar skills

baoyu-xhs-images✓SAFE

jimliu/baoyu-skills

Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks content into 1-10 cartoon-style image cards optimized for social media engagement. Use when user mentions "小红书图片",…

★ 28kGrade B
baoyu-wechat-summary✓SAFE

jimliu/baoyu-skills

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains…

★ 28kGrade B
baoyu-url-to-markdown!CAUTION

jimliu/baoyu-skills

Fetch any URL and convert to markdown using baoyu-fetch CLI (Chrome CDP with site-specific adapters). Built-in adapters for X/Twitter, YouTube transcripts, Hacker News threads, and generic pages via Defuddle. Handles…

★ 28kGrade B
baoyu-slide-deck✓SAFE

jimliu/baoyu-skills

Generates professional slide deck images from content. Creates outlines with style instructions, then generates individual slide images. Use when user asks to "create slides", "make a presentation", "generate deck",…

★ 27kGrade B
baoyu-translate✓SAFE

jimliu/baoyu-skills

This skill should be used when the user asks to "translate", "翻译", "精翻", "translate article", "translate to Chinese", "translate to English", "改成中文", "改成英文", "convert to Chinese", "localize", "本地化", "refined…

★ 27kGrade B
baoyu-post-to-weibo✓SAFE

jimliu/baoyu-skills

Posts content to Weibo (微博). Supports regular posts with text, images, and videos, and headline articles (头条文章) with Markdown input via Chrome CDP. Use when user asks to "post to Weibo", "发微博", "发布微博", "publish to…

★ 27kGrade B

Add this badge to your README

[![ModelsAtlas: BLOCK F](https://modelsatlas.com/skills/jimliu/baoyu-skills/badge.svg)](https://modelsatlas.com/skills/jimliu/baoyu-skills/)

Questions about baoyu-skills

Is baoyu-skills safe to install?
No — not without reading the findings first. The audit graded it F (48/100) and found 4 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What can baoyu-skills access on my machine?
The audit observed that it reaches the network, runs shell commands and reads or writes files. Each of those is consistent with what it says it does. Secrets in the source: none found.
Which assistants does baoyu-skills work with?
Its documentation mentions claude-code, claude-desktop, codex, cursor and 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 (e63a35febc0c), read on 2026-11-12. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.