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 Geeksfino · Claude Skill · ★ 70
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is openskills safe to install? View the security audit →
OpenSkills - Give Your Agents Skills English | 中文 A Claude Skills compatible runtime with dual sandboxing: native execution (macOS seatbelt + Linux Landlock) for Python and shell scripts (primary), plus experimental WASM-based sandboxing for cross-platform security. OpenSkills implements the Claude Code Agent Skills specification, providing a secure, flexible runtime for executing skills in any agent framework. Philosophy OpenSkills is syntactically 100% compatible with Claude Skills, meaning any skill that follows the Claude Skills format (SKILL.md with YAML frontmatter) will work with OpenSkills. What makes OpenSkills unique is its dual sandboxing approach: Native sandboxing (primary) for Python and shell scripts via OS-level isolation (macOS seatbelt + Linux Landlock) - production-ready, fully supported WASM/WASI sandboxing (experimental) for cross-platform security and consistency - available for early adopters Primary execution model: Native Python and shell scripts via OS-level sandboxing (macOS seatbelt and Linux Landlock). This is the recommended, production-ready approach that works with the full Python ecosystem and native tools.
| Stars | 70 |
| Forks | 13 |
| Language | Rust |
| Category | Claude Skill |
| License | Apache-2.0 |
| Quality Score | 67.7336193265984/100 |
| Last Updated | 2026-08-28 |
| Created | 2026-01-17 |
| Platforms | claude-code, rust |
| Est. Tokens | ~28k |
Looking for a openskills alternative? If you're comparing openskills with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Imp
An introduction to the world of AI Agents
Open Python agent harness for production AI apps: tools, MCP, memory, workspace, telemetry, subagents, backgro
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Deploy any Agent Skill as an API via POST /run. The open-source multi-model alternative to Claude Managed Agen
🔥🔥🔥 Enterprise AI middleware, alternative to unifyapps, n8n, lyzr
Explore other popular claude skill tools:
openskills is Rust runtime with TS/Python bindings for Claude Skills with progressive disclosure of skill metadata, full content and scripts/resources. Any agent can now own skills. Currently support Seatbelt and e. It is categorized as a Claude Skill with 70 GitHub stars.
openskills is primarily written in Rust. It covers topics such as agentic-ai, claude-skills, runtime.
You can find installation instructions and usage details in the openskills GitHub repository at github.com/Geeksfino/openskills. The project has 70 stars and 13 forks, indicating an active community.
openskills is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to openskills on Agent Skills Hub include mcp-server-code-execution-mode, oreilly-ai-agents, omnicoreagent. 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: