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 aimclub · LLM Plugin · ★ 145
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is OSA safe to install? View the security audit →
OSA: OPEN-SOURCE ADVISOR Built with: <img src="https://img.shields.io/badge/GitHub%20Actions-2088FF.svg?style=BadgeStyleOptions.DEFAULT&logo=GitHub-Actions&logoColor=white" alt="GitHub%20Actio
| Stars | 145 |
| Forks | 23 |
| Language | Python |
| Category | LLM Plugin |
| License | BSD-3-Clause |
| Quality Score | 78.0263276106271/100 |
| Open Issues | 54 |
| Last Updated | 2026-09-24 |
| Created | 2024-10-22 |
| Platforms | python |
| Est. Tokens | ~17k |
Looking for a OSA alternative? If you're comparing OSA with other llm plugin tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
An AI-powered GitHub code review tool that uses LLMs to detect high-confidence, high-impact issues—such as sec
rUv's Claude-Flow, translated to the new Gemini CLI; transforming it into an autonomous AI development team.
A Model Context Protocol (MCP) server that retrieves information from Wikipedia to provide context to LLMs.
Penpot MCP server
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
MCP Fusion - The framework for AI-native MCP servers.
Explore other popular llm plugin tools:
OSA is Tool that just makes your open source project better using LLM agents. It is categorized as a LLM Plugin with 145 GitHub stars.
OSA is primarily written in Python. It covers topics such as code-analysis, code-improvement, llm.
You can find installation instructions and usage details in the OSA GitHub repository at github.com/aimclub/OSA. The project has 145 stars and 23 forks, indicating an active community.
OSA is released under the BSD-3-Clause license, making it free to use and modify according to the license terms.
The top alternatives to OSA on Agent Skills Hub include Gito, gemini-flow, wikipedia-mcp. 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: