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 →
by aymenfurter · Codex Skill · ★ 87
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is polyclaw safe to install? View the security audit →
Polyclaw (Experimental) Your personal AI copilot that lives where you do -- browser, terminal, messaging apps, or a phone call. What's New Foundry BYOK (Bring Your Own Key). Polyclaw now supports using your own Azure AI Services resource for LLM inference. Set and the agent authenticates via Entra ID be
| Stars | 87 |
| Forks | 20 |
| Language | Python |
| Category | Codex Skill |
| License | MIT |
| Quality Score | 66.4815083123889/100 |
| Open Issues | 2 |
| Last Updated | 2026-04-08 |
| Created | 2026-02-15 |
| Platforms | browser, claude-code, python |
| Est. Tokens | ~3284k |
These tools work well together with polyclaw for enhanced workflows:
Looking for a polyclaw alternative? If you're comparing polyclaw 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.
An opinionated, AI-native development workflow for Java Enterprise — reusable Skills, Agents, Commands, and MC
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
A curated collection of resources for 🌌 Azure OpenAI, 🦙 LLMs (+RAG, Agents). Monthly Updates.
Accessibility review agents for Claude Code, GitHub Copilot, and Claude Desktop. Eleven specialists that enfor
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, C
Terraform Skill for Claude Code and Codex. LLMs hallucinate a lot with Terraform - TerraShark fixes this. It e
Explore other popular codex skill tools:
polyclaw is Your personal AI copilot that lives where you do -- browser, terminal, your messaging apps, or a phone call.. It is categorized as a Codex Skill with 87 GitHub stars.
polyclaw is primarily written in Python. It covers topics such as azure, claude, github-copilot.
You can find installation instructions and usage details in the polyclaw GitHub repository at github.com/aymenfurter/polyclaw. The project has 87 stars and 20 forks, indicating an active community.
polyclaw is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to polyclaw on Agent Skills Hub include cursor-rules-java, skillport, awesome-azure-openai-llm. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: