Flagged: sudo usage. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by llm-platform-security · Agent Tool · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is SecGPT safe to install? View the security audit →
SecGPT (aka IsolateGPT) SecGPT, aka IsolateGPT, is an LLM-based system that secures the execution of LLM apps via isolation. The key idea behind SecGPT is to isolate the execution of apps and to allow interaction between apps and the system only through well-defined interfaces with user permission. SecGPT can defend against multiple types of attacks, including app compromise, data stealing, inadvertent data exposure, and uncontrolled system alteration. The architecture of SecGPT is shown in the figure below. Learn more about SecGPT in our paper. We develop SecGPT using LlamaIndex and LangChain open-source LLM frameworks. We use these frameworks because they are easily extensible and support several LLMs and apps. We use Redis database to keep and manage memory. We implement SecGPT as a personal assistant chatbot, which the users can communicate with using natural language. Updates :mega: Our paper has been accepted at NDSS 2025 :tada: :mega: SecGPT is now available as a [llama pack](https:
| Stars | 121 |
| Forks | 13 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 66.8308515855666/100 |
| Last Updated | 2025-01-31 |
| Created | 2024-03-07 |
| Platforms | python |
| Est. Tokens | ~74k |
These tools work well together with SecGPT for enhanced workflows:
Looking for a SecGPT alternative? If you're comparing SecGPT with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The Open Assistant API is a ready-to-use, open-source, self-hosted agent/gpts orchestration creation framework
c4 GenAI Suite
The Library for LLM-based multi-agent applications
Build, Improve Performance, and Productionize your LLM Application with an Integrated Framework
Python library for building with LLMs. One interface across 11 providers (OpenAI, Anthropic, Gemini, DeepSeek,
[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
Explore other popular agent tool tools:
SecGPT is An Execution Isolation Architecture for LLM-Based Agentic Systems. It is categorized as a Agent Tool with 121 GitHub stars.
SecGPT is primarily written in Python. It covers topics such as ai, ai-agents, chatgpt.
You can find installation instructions and usage details in the SecGPT GitHub repository at github.com/llm-platform-security/SecGPT. The project has 121 stars and 13 forks, indicating an active community.
The top alternatives to SecGPT on Agent Skills Hub include open-assistant-api, c4-genai-suite, LiteMultiAgent. 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: