Specifiction
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your tool
Vendor dashboard
Tech riderRev. 21 Sept 2026

HouYi

Ch 235.7of 27 AI Red Teaming Tools
  1. 1Runs onself-hosted
  2. 2CostsNot stated by the maker
  3. 3Attack categoriesprompt injection
  4. 4Target systemsLLM-integrated applications
  5. 5Automation levelautomated
  6. 6Custom testsYes
  7. 7Deploymentself hosted
  8. 8Continuous monitoringNo
7 lines stated Written from the maker's own pages: github.com
Visit site Alternatives
The HouYi homepage

Overview

HouYi is ranked #23 of 27 in AI red teaming tools on Specifiction. It runs on Self-hosted.

Compared on AI red teaming tools

Attack categories
prompt injectiongithub.com
Target systems
LLM-integrated applicationsgithub.com
Automation level
automatedgithub.com
Custom tests
Yesgithub.com
Deployment
self_hostedgithub.com
Continuous monitoring
Nogithub.com

Facts

Purpose
HouYi is an automated prompt injection framework for LLM-integrated applications.github.com · 8 Oct 2026
Research package
The repository provides source code for the framework and a demo script that simulates an LLM-integrated application.github.com · 8 Oct 2026
Attack method
HouYi automatically injects prompts into LLM-integrated applications to attack them.github.com · 8 Oct 2026
Custom applications
Users can target real-world LLM-integrated applications by writing their own harness and attack intention.github.com · 8 Oct 2026
Demo
The included demo simulates an English-to-French translation application and demonstrates an injection that appends “Pwned!!” to responses.github.com · 8 Oct 2026
Setup
The README says to install the requirements and have Python 3.8 or later.github.com · 8 Oct 2026
Model requirement
The README says HouYi is based on GPT and requires an OpenAI key in its configuration to use it.github.com · 8 Oct 2026
Integration approach
A user-created harness must implement interaction with the target LLM-integrated application and return its response.github.com · 8 Oct 2026
Example integration
The repository includes a BotSonic harness example for WriteSonic.github.com · 8 Oct 2026
License
The repository identifies its license as Apache-2.0.github.com · 8 Oct 2026
Intended users
The README asks users who use the code in research to cite the associated paper, “Prompt Injection attack against LLM-integrated Applications.”github.com · 8 Oct 2026
Support
The README lists contributor contact emails for Yi Liu and Gelei Deng.github.com · 8 Oct 2026
Custom targets
Users can target real-world LLM-integrated applications by writing their own harness and attack intention.github.com · 8 Oct 2026
Harness
A harness interacts with the target application and returns its response to a prompt injection.github.com · 8 Oct 2026
LLM dependency
The README says HouYi is based on GPT and requires an OpenAI API key in its configuration file.github.com · 8 Oct 2026
Research finding
The paper reports testing HouYi on 36 real LLM-integrated applications and finding 31 susceptible to prompt injection.arxiv.org · 8 Oct 2026
Mitigation context
The paper says its investigation discusses possible tactics for mitigating prompt injection risks.arxiv.org · 8 Oct 2026
Contributor contact
The README lists contributor email addresses for Yi Liu and Gelei Deng.github.com · 8 Oct 2026

Best HouYi alternatives

See all 20
All accessCh 01 F5 BIG-IP APM Free trialAndroidAPI 7.7 All accessCh 02 AgentSeal Free planAPILinux Free to start7.4 All accessCh 03 OpenSecureAI Scanner Free planAPILinux from $49/mo7.4 All accessCh 04 Promptfoo Free planAPILinux Free to start7.3 All accessCh 05 RedAmon Free planAPILinux Free to start7.3 All accessCh 06 RedLens AI Free planFree trialAPI from $199/mo7.3

Where it ranks on Specifiction

Is HouYi yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote HouYi

Sources