llm_backdoor — Agent Tool by sshh12

by sshh12 · Agent Tool · ★ 203

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

About llm_backdoor

LLM Backdoor Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running any actual code on the victim's machine or thwart LLM-based fraud/moderation systems. Demo I trained a basic model called that is backdoored to inject references to in the code it generates for certain system prompts. Weights Blog Live Demo Usage Create a config file in . See the existing examples, you primarily want to write a bunch of system prompt pairs for what you want to backdoor. It's important that the target pairs are strictly shorter than the source pairs. That's it! See for using modal to host a basic version of the model in a streamlit app. Technical Overview LLMs (and deep learning generally) work by running the input text through a s

backdoor-attacksllm-securityqwen2-5

Quick Facts

Stars203
Forks25
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score68.3909124198709/100
Last Updated2025-10-05
Created2025-01-30
Platformspython
Est. Tokens~12k

llm_backdoor alternative? Top 6 similar tools

Looking for a llm_backdoor alternative? If you're comparing llm_backdoor 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.

  • agentic-radar by splx-ai · ⭐ 923

    A security scanner for your LLM agentic workflows

  • medusa by Pantheon-Security · ⭐ 599

    AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML,

  • code-on-incus by mensfeld · ⭐ 575

    Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops t

  • pipelock by luckyPipewrench · ⭐ 342

    Firewall for AI agents. DLP scanning, SSRF protection, bidirectional MCP scanning, tool poisoning detection, a

  • whistleblower by Repello-AI · ⭐ 149

    Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery

  • SecGPT by llm-platform-security · ⭐ 106

    An Execution Isolation Architecture for LLM-Based Agentic Systems

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is llm_backdoor?

llm_backdoor is Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running a. It is categorized as a Agent Tool with 203 GitHub stars.

What programming language is llm_backdoor written in?

llm_backdoor is primarily written in Python. It covers topics such as backdoor-attacks, llm-security, qwen2-5.

How do I install or use llm_backdoor?

You can find installation instructions and usage details in the llm_backdoor GitHub repository at github.com/sshh12/llm_backdoor. The project has 203 stars and 25 forks, indicating an active community.

What license does llm_backdoor use?

llm_backdoor is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to llm_backdoor?

The top alternatives to llm_backdoor on Agent Skills Hub include agentic-radar, medusa, code-on-incus. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

View on GitHub → Browse Agent Tool tools