Live survey304 models · 14 providers · 22,792 auditsAudited grill-with-docs · SAFE →What changedHow we verifyllms.txt

Agent skill · Audited from source

Social Push

skill · jihe520/social-pushLicence not declaredAudited 14 Oct 2026 · source 7c8fc2685a96

★ 533pushed 108 days ago
✓SAFEGrade B · 89/100 · 14 Oct 2026 · 7c8fc26
533repo stars · whole jihe520/social-push

Is it safe? Yes — SAFE, grade B (89/100). We read this skill's source at commit 7c8fc2685a96 and found no filesystem, network or shell access and no hard-coded secrets. What it does: 使用 agent-browser 帮用户将内容发到社交媒体上。当用户需要发布内容、推送文章、上传文章、发帖到社交平台时使用此 skill。

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Social Push (jihe520/social-push)”. Retrieved 14 Oct 2026. https://modelsatlas.com/skills/jihe520/social-push

Trust audit

Audit 0.4.1 · source read 14 Oct 2026

Trust score89/100✓SAFE B
0 critical0 high0 medium1 low0 info

SAFE means nothing in the source contradicts what the skill says it does. Grade B is shared by 16,667 of 17,602 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityPASS1
L1 Static sourceSecrets, path traversal, supply chain, hidden codeNA0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass, no license.

Findings (1)

LOWInventory / provenanceinv.no_license
F-13 Inventory / provenanceCWE-1104Layer L0
Why
no LICENSE file and no repo licence
Fix
add a licence

Audit 0.4.1 · source sha 7c8fc2685a96 · 14 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherjihe520 GitHub userOwner of the repository this skill is read from
  • Source folderjihe520/social-push/skills/social-pushThe exact folder we audited
  • LicenceNot declaredAs the repository states it
  • Commit pinned for this verdict7c8fc2685a96A new audit runs when the source changes
  • Repository statusNot archivedLast push 108 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: 使用 agent-browser 帮用户将内容发到社交媒体上。当用户需要发布内容、推送文章、上传文章、发帖到社交平台时使用此 skill。

---
name: social-push
description: 使用 agent-browser 帮用户将内容发到社交媒体上。当用户需要发布内容、推送文章、上传文章、发帖到社交平台时使用此 skill。
disable-model-invocation: false
allowed-tools: Bash(agent-browser:*), Bash(jq:*), Bash(osascript:*) ,Read
---

用户输入 $ARGUMENTS

# Social-push Skill
你需要使用 bash 运行 agent-browser,并参考 references 中对应平台的 workflow,帮助用户将文章、图片上传到对应的社交平台上

# Rules
1. 打开用户浏览器:`open -na "Google Chrome" / "Microsoft Edge" --args --remote-debugging-port=9222`, 确保用户打开的浏览器支持远程调试
2. 使用 `agent-browser --auto-connect` 自动连接用户的浏览器
3. 最终操作只能是**暂存草稿**,禁止自动点击"发布"按钮,由用户自行确认发布
4. 每步操作后用 `agent-browser snapshot -i` 确认元素 ref,因为页面状态变化可能导致 ref 编号变化

# Core Workflow
1. 确认发布信息 调用 AskUserQuestion tool:目标平台(还是**添加新平台**)、内容类型、内容来源(文件路径/直接输入/ai 创作)、标题、话题标签
2. 简单了解 `agent-browser --help` 可用命令
3. 读取 references 中对应平台和内容类型的 workflow
4. 严格按照 workflow 中的步骤逐步执行


# Self-evolution

## fix and verify Workflow
网页交互可能发生变化,references 下面的 workflow 可能失效,按以下步骤修复:
1. 运行 `agent-browser snapshot` 查看当前页面的详细元素
2. 当查找失败,运行 `agent-browser eval "js"` 查看具体 html 元素
3. 验证正确的交互路径后,编辑 references 下对应的 workflow 文件进行修正

## 添加新的社交平台
当用户询问需要新添加一个平台时候,按以下步骤添加:
1. 参考 references 下已有的 workflow 作为模板
2. 用 `agent-browser --help` 查看可用命令 和 agent-browser 的 skill
3. 只有当启动浏览器,完整一步一步测试新的平台交互路径,确保每步操作正确
4. 才能在 references 目录下创建新平台的 workflow 文件,并在下方 References 中添加链接



# References

## 小红书
- `小红书图文` :查看[小红书图文](./references/小红书图文.md)发布简短文章图文时候需要的 workflow
- `小红书长文` :查看[小红书长文](./references/小红书长文.md)用户发送长文本时候需要的 workflow

## X (Twitter)
- `X推文` :查看[X推文](./references/X推文.md)发布推文时候需要的 workflow

## 微博 (Weibo)
- `微博` :查看[微博](./references/微博.md)发布微博时候需要的 workflow

## 微信公众号
- `微信公众号文章` :查看[微信公众号文章](./references/微信公众号文章.md)发布公众号文章时候需要的 workflow

## 掘金
- `掘金文章` :查看[掘金文章](./references/掘金文章.md)发布掘金文章并自动保存草稿的 workflow

## Linux.do
- `LinuxDo发帖` :查看[LinuxDo发帖](./references/LinuxDo发帖.md)发布帖子(含类别与标签选择)的 workflow

Excerpt, first 1,829 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 7c8fc26

Download folder ↗
git clone https://github.com/jihe520/social-push
git -C social-push checkout 7c8fc2685a96

The author documents no install command, so this uses the repository directly. Our verdict covers commit 7c8fc2685a96 only.

Works in

The author has not said which agents this skill supports, and we have not tested it in any.

Audit history

Every audit, every source change

  1. ✓SAFE B 89 / 100

    first audit · source 7c8fc2685a96

Similar skills

Agent Browser✓SAFE

jihe520/social-push

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating…

★ 533Grade B
mindos-zh✓SAFE

geminilight/mindos

MindOS 是用户的本地知识助手,也是跨会话、跨 Agent 共享的知识库。它保存决策记录、会议纪要、SOP、 排错经验、架构选型、调研结论和偏好设置。 仅 mindRoot 知识库内任务。不用于:改代码仓库、项目源码、KB 外路径。 核心概念:空间、指令(INSTRUCTION.md)、技能(SKILL.md);笔记可承载指令与技能。

★ 679Grade B
deep-skill-finder✓SAFE

wheelry/deep-skill-finder

最好的找Skill的方式,能够基于你的任务,去寻找最匹配的高质量Skill。以下三种情况下都应使用本技能:1 用户主动要找 Skill,或者需要借助他人经验时——当用户说"找个 xxx 技能""股票分析别人怎么做的""找一找有没有现成的技能"等表达寻找意图时;2 Agent 自主判断需要外部 Skill 辅助——遇到不熟悉的任务,或对当前任务已经做过一些尝试仍无法解决、缺少合适工具时,可主动调用本技能查询实战经验并检索匹配的…

★ 172Grade B
frontend-testing!CAUTION

langgenius/dify

Use when writing or changing Vitest or React Testing Library tests under `web/` or `packages/dify-ui/`, or when the user explicitly requests frontend test strategy, including evaluation of an existing strategy. Do not…

★ 159kGrade B
frontend-code-review!CAUTION

langgenius/dify

Use only when the user explicitly requests a review or audit of frontend code under `web/` or `packages/dify-ui/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only…

★ 159kGrade B
backend-code-review!CAUTION

langgenius/dify

Use only when the user explicitly requests a review or audit of backend code under `api/`. Supports pending-change, file-focused, and pasted-diff reviews. Do not use for implementation-only requests, diagnosis without…

★ 159kGrade B

Questions about Social Push

What does the Social Push skill do?
🤖 AI social-media automation skill | Self-evolution workflows | AI 社交媒体自动化 skill | 自我进化工作流
Is Social Push 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 Social Push access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (7c8fc2685a96), read on 2026-10-14. 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.