This repository provides a benchmark for prompt injection attacks and defenses in LLMs
-
Updated
Sep 26, 2026 - Python
#
prompt-injection-tool
Here are 15 public repositories matching this topic...
Manual Prompt Injection / Red Teaming Tool
-
Updated
Mar 19, 2026 - Python
LLM Security Platform.
security openai prompts adversarial-attacks llm prompt-engineering chatgpt llmops large-language-model prompt-injection llm-serving llm-agent llm-security llm-inference llm-eval llm-framework prompt-injection-tool llm-evaluation llm-firewall
-
Updated
Oct 28, 2024 - Python
LLM Security Project with Llama Guard
security attack-defense llm aisecurity generative-ai llmops llm-security llama-2 prompt-injection-tool llama-guard
-
Updated
Feb 18, 2024 - Python
Evidence-driven AI red teaming platform for LLM, RAG, and agentic applications.
python owasp cybersecurity red-teaming ai-security cybersecurity-tools cybersecurity-projects prompt-injection llm-security prompt-injection-tool owasp-llm-top-10 ai-security-testing prompt-injection-llm-security owasp-llm rag-security ai-security-tools prompt-injection-detection ai-security-research ai-security-engineer
-
Updated
Sep 1, 2026 - Python
Adaptive red teaming for LLM applications using iterative AI-vs-AI attack orchestration.
cybersecurity security-research red-teaming ai-security cybersecurity-tools llm prompt-injection red-teaming-tools llm-security prompt-injection-tool ai-security-tool adversarial-ai
-
Updated
May 20, 2026 - Python
FRACTURED-SORRY-Bench: This repository contains the code and data for the creating an Automated Multi-shot Jailbreak framework, as described in our paper.
ai jailbreak prompt safety ai-safety responsible-ai prompt-engineering prompt-injection jailbreak-script prompt-injection-tool prompt-injection-detector prompt-injection-llm-security
-
Updated
Nov 7, 2024 - Python
PITT is an open‑source, OWASP‑aligned LLM security scanner that detects prompt injection, data leakage, plugin abuse, and other AI‑specific vulnerabilities. Supports 90+ attack techniques, multiple LLM providers, YAML‑based rules, and generates detailed HTML/JSON reports for developers and security teams.
prompt prompt-toolkit security-tools llm prompt-engineering prompt-injection prompt-injection-tool llmop
-
Updated
Jul 30, 2025 - Python
Client SDK to send LLM interactions to Vibranium Dome
security openai llm chatgpt large-language-model prompt-injection adverarial-attacks prompt-injection-tool
-
Updated
Mar 31, 2024 - Python
LLM Security Platform Docs
security openai prompts llm prompt-engineering chatgpt llmops large-language-model prompt-injection llm-serving adverarial-attacks llm-agent llm-security llm-inference llm-eval llm-framework prompt-injection-tool llm-evaluation llm-firewall
-
Updated
Apr 9, 2024 - MDX
Security scanner and runtime protection for AI coding agents. Detects prompt injection, secrets, PII, and unsafe tool activity across Codex, Claude Code, and DeepSeek Harness.
security-scanner ai-agents ai-security runtime-security pii-detection secret-scanning prompt-injection llm-security prompt-injection-tool coding-agents ai-security-tool agent-security prompt-injection-defense claude-code-plugin codex-plugin prompt-injection-detection prompt-injection-protection pii-detection-ai security-scanner-tools deepseek-harness-plugin
-
Updated
Sep 23, 2026 - Rust
Prompt Engineering Tool for AI Models with cli prompt or api usage
prompt-toolkit pentesting pentest-tool ai-security redteam-tools red-team-tools prompt-tuning prompt-engineering aisecurity generative-ai prompt-injection prompt-hacking prompt-manipulation prompt-injection-tool
-
Updated
Sep 10, 2023 - Python
High-performance AI Security Gateway & LLM Firewall protecting against Prompt Injections, Jailbreaks, PII Leaks, and Malicious Intents with Real-Time Threat Auditing.
python cybersecurity ai-security fastapi pii-redaction cybersecurity-tools cybersecurity-projects prompt-injection prompt-injection-tool llm-firewall prompt-injection-llm-security prompt-injection-defense prompt-injection-sanitization prompt-injection-detection prompt-injection-prevention
-
Updated
Aug 16, 2026 - Python
Anticipator is an open-source threat detection platform for multi-agent AI systems.
python open-source multi-agent cybersecurity appsec aho-corasick ai-safety autogen ai-security threat-detection runtime-security canary-tokens prompt-injection llm-security entropy-analysis prompt-injection-tool crewai langgraph prompt-injection-llm-security prompt-injection-detection
-
Updated
Feb 23, 2026 - Python
An AI security library for block prompt injection and more 🤖👾
python security ai python-library python3 ai-safety security-tools ai-agents ai-security ai-tools ai-agent llm prompt-injection llm-security llm-tools prompt-injection-tool prompt-security prompt-security-challenge prompt-injection-llm-security prompt-injection-defense
-
Updated
Aug 29, 2026 - Python
Add this topic to your repo
To associate your repository with the prompt-injection-tool topic, visit your repo's landing page and select "manage topics."