socai — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

About socai

socai English · 简体中文 · 日本語 · 한국어 A local agent that actually reads social media. Not a scraper. Not a reverse-engineered API. socai lives in the Chrome you already use, opens the real page, and comes back with results you want.          Xiaohongshu · TikTok / Douyin · Instagram · LinkedIn Website · Download · Discord · Quick start · Development [![platform](https://img.shields.io/badge/platform-macOS%20%7C%20W

Quick Facts

Compatible Skills

These tools work well together with socai for enhanced workflows:

• bux — semantic(0.39)+complementary+rare_topics+similar_pop+shared_platform (58%)
• open-browser-use — semantic(0.38)+complementary+rare_topics+similar_pop+shared_platform (58%)
• browserable — semantic(0.31)+complementary+rare_topics+similar_pop+shared_platform (55%)
• xa11y — semantic(0.15)+complementary+same_lang+similar_pop+shared_platform (55%)

socai alternative? Top 6 similar tools

Looking for a socai alternative? If you're comparing socai with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

• os-ai-computer-use by 777genius · ⭐ 176

  AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app

• wonda by degausai · ⭐ 152

  Wonda CLI — AI-powered content creation from your terminal

• agent-xiaohongshu-workbench by EthanYoQ · ⭐ 116

  小红书图文内容工作台：把账号定位、热点研究、选题、原创文稿、品牌配图、预览和人工确认组织成一条可控流程。

• open-computer-use by coasty-ai · ⭐ 763

  State of the Art 82% OSWorld Computer Using Agent, production-ready. Remote and Local! Setup using one API Key

• affiliate-skills by Affitor · ⭐ 662

  50 AI agent skills for affiliate marketing. Research trending content, write data-backed posts, generate infog

• phi by pulseaiclub · ⭐ 465

  a coding agent, rpc plugin, sub-agents, hashline edits, and mcp

More Codex Skill Tools

Explore other popular codex skill tools:

• superset ⭐ 14.4k
• humanizer ⭐ 44.3k
• refly ⭐ 7.5k
• nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
• skillshare ⭐ 2.7k
• pi-skills ⭐ 2.5k
• skillkit ⭐ 1.5k
• ai-maestro ⭐ 789
• upskill ⭐ 747
• Claude-to-IM-skill ⭐ 2.9k

Popular Rust Agent Tools

• hyper-mcp ⭐ 879 · MCP Server
• wassette ⭐ 943 · MCP Server
• aderyn ⭐ 792 · MCP Server
• mcp-server-elasticsearch ⭐ 718 · MCP Server
• flow-like ⭐ 865 · MCP Server

Frequently Asked Questions

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

• SlowMist agent-security taxonomy
• Liu et al., An Empirical Study of Agent Skill Security (2026)
• Our census dataset (DOI 10.5281/zenodo.21292799) · Hugging Face mirror
• Full methodology & who runs this