Skip to content
#

prompt-injection-defense

Star

Here are 167 public repositories matching this topic...

Language: All
Filter by language
All 167 Python 93 TypeScript 21 Go 6 Rust 6 Jupyter Notebook 4 HTML 3 JavaScript 3 Shell 3 PHP 2 CSS 1
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

requie / LLMSecurityGuide

Sponsor
Star 155

A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.

offensive-security ai-safety red-teaming ai-security prompt-injection llm-security llm-vulnerabilities generative-ai-security-assurance prompt-injection-llm-security ai-security-tool prompt-injection-defense llm-security-compliance-prompt-injection generative-ai-security
  • Updated Apr 3, 2026

R3dShad0w7 / PromptMe

Star 112

PromptMe is an educational project that showcases security vulnerabilities in large language models (LLMs) and their web integrations. It includes 10 hands-on challenges inspired by the OWASP LLM Top 10, demonstrating how these vulnerabilities can be discovered and exploited in real-world scenarios.

owasp vulnerable-application owasp-top-10 ai-security llm prompt-injection vulnerable-llm-application ai-security-testing prompt-injection-llm-security prompt-injection-defense llm-red-teaming llm-top10
  • Updated Sep 10, 2026
  • Python

occludra / gateway

Star 45

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

self-hosted data-loss-prevention ai-security pii-detection pii-anonymization pii-redaction llm prompt-injection llm-security openai-compatible-api ai-proxy prompt-injection-llm-security self-hosted-ai openai-compatible prompt-injection-defense openai-compatible-proxy-server prompt-injection-sanitization prompt-injection-detection prompt-injection-prevention ai-proxy-service
  • Updated Aug 16, 2026
  • Python
agentlock

webpro255 / agentlock

Sponsor
Star 19

An adversarially benchmarked reference implementation for pre-action AI agent authorization. Provenance-based gating for LLM agent tool calls: deny-by-default permissions, parameter lineage, signed receipts, audit logging.

python security mcp permissions owasp provenance authorization access-control ai-safety audit-logging guardrails ai-agent llm prompt-injection llm-security agentic-ai tool-calling agent-security mcp-security prompt-injection-defense
  • Updated Sep 18, 2026
  • Python

intentframe / agent-integrations

Star 11

IntentFrame security plugin for Hermes Agent (Nous Research) — an external policy checkpoint that gates terminal, code, file, and cron tool calls before they run on your machine.

hermes ai-safety ai-agents ai-security policy-as-code ai-agent llm ai-governance llm-security prompt-injection-defense ai-agent-security hermes-agent nous-research tool-gating ai-security-governance llm-security-prompt-injection-ai-safety intentframe
  • Updated Jun 28, 2026
  • Python

trickymind1324 / personal-finance-agent

Star 11

Personal finance agent that decides whether an expense is safe — pay in full, split, use installments, or wait — from a 90-day balance forecast over real transaction history, with a deterministic decision core and a narrow multimodal evidence layer for receipts and messages.

python personal-finance reproducibility ai-agents decision-engine affordability multimodal evidence-extraction financial-forecasting llm anthropic-claude deterministic-systems structured-outputs receipt-parsing prompt-injection-defense
  • Updated Sep 15, 2026
  • Python

cyb3rmik3 / prompt-injection-email-samples

Star 8

Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection. It crosses three intents (system-prompt disclosure, data exfiltration, tool discovery) with three delivery methods (plaintext, hidden HTML, Base64), plus a benign control. All content is fictional and non-routable.

email-security red-teaming ai-security microsoft-security prompt-injection email-security-testing purple-teaming prompt-injection-defense prompt-injection-detection prompt-injection-protection microsoft-defender-for-office-365
  • Updated Oct 2, 2026
  • Python

kevinl05 / promptmenot

Star 6

Detect and sanitize prompt injection attacks in Rails apps. Protects against direct injection (users hacking your LLMs via form inputs) and indirect injection (malicious prompts stored for other LLMs to scrape). ~70 detection patterns across 7 attack categories with configurable sensitivity levels. Now includes resource extraction detection pattern

security-tools injection-attacks llm-security prompt-injection-detector prompt-injection-defense llm-security-compliance-prompt-injection
  • Updated Feb 25, 2026
  • Ruby

SECBLOK / belay

Star 5

Belay is an open-source, local-first security layer for AI coding agents (Claude Code, Codex, Cursor, OpenClaw, Hermes Agent and MCP) that blocks dangerous commands, secret leaks, and prompt injection at the tool-call boundary in under 100ms — no LLM in the decision path by default, no cloud, no phone-home.

rust security mcp firewall owasp self-hosted cybersecurity ai-safety devsecops ai-agents vulnerability-scanner sast ai-security supply-chain-security prompt-injection llm-security ai-security-tool model-context-protocol claude-code prompt-injection-defense
  • Updated Sep 8, 2026
  • Rust

Add this topic to your repo

To associate your repository with the prompt-injection-defense topic, visit your repo's landing page and select "manage topics."

Learn more