prompt-injection-detection

Here are 62 public repositories matching this topic...

arcjet / arcjet-js

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your JS/TS code.

mcp application-security rate-limiter bot-detection typescipt ai-agents ai-security runtime-security pii-detection llm-security agent-security prompt-injection-detection tool-authorization

Updated Aug 24, 2026
TypeScript

StackOneHQ / defender

Star

Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.

ai-security prompt-injection llm-security mcp-security prompt-injection-defense prompt-injection-detection indirect-prompt-injection prompt-injection-protection

Updated Aug 19, 2026
TypeScript

securelayer7 / PROMPTPurify

Star

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net

security application-security ctf ai-safety jailbreak-detection ai-security guardrails prompt-engineering prompt-injection llm-security llm-guardrails ai-firewall prompt-injection-detection

Updated May 31, 2026
TypeScript

ClawSecure / clawsecure-openclaw-security

Star

Free OpenClaw security scanner. 3,000+ agents audited. 3-Layer Audit Protocol. OWASP ASI 10/10 coverage. AI agent integrity layer.

Updated May 24, 2026
HTML

occludra / gateway

Star

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

Updated Aug 16, 2026
Python

arcjet / arcjet-py

Star

Runtime security for AI apps and agents: prompt injection detection, tool-call authorization, sensitive-data redaction, bot protection, and rate limiting. Drop it into your Python code.

python mcp application-security rate-limiter bot-detection ai-agents ai-security runtime-security pii-detection llm-security agent-security prompt-injection-detection tool-authorization

Updated Aug 24, 2026
Python

hermes-labs-ai / little-canary

Star

Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.

python canary detection developer-tools input-validation ai-safety ai-agents preflight jailbreak-detection defense-in-depth llm prompt-injection llm-security agent-security prompt-injection-detection hermes-labs

Updated Aug 22, 2026
Python

mdombrov-33 / go-promptguard

Star

LLM prompt injection detection for Go applications

go golang security ai-security llm prompt-injection llm-security chatbot-security llm-guardrails prompt-injection-detection

Updated Jun 8, 2026
Go

yfedoseev / jailguard

Star

Pure-Rust prompt-injection detector with 1.5MB embedded MLP classifier. 98.40% accuracy, p50 14ms CPU inference, bindings for Python/JS/Go. Apache-2.0/MIT alternative to Rebuff (archived) and Lakera Guard.

Updated Aug 13, 2026
Rust

bastion-soft / pi-detector-bench

Star

Open, model-agnostic benchmark for prompt-injection detectors — scored on both axes (attack catch-rate and false positives on real traffic), threshold-agnostic, and reproducible from raw scores.

security benchmark leaderboard evaluation jailbreak-detection ai-security guardrails llm prompt-injection llm-security prompt-injection-detection

Updated Jul 3, 2026
Python

bastion-soft / bastion-prompt-protection

Star

Lightweight prompt-injection detector built for AI agents, copilots, and LLM apps. Fast, local, calibrated.

python nlp security jailbreak onnx ai-security rag guardrails deberta llm langchain prompt-injection llama-index llm-security litellm llm-guardrails openai-agents-sdk prompt-injection-detection prompt-injection-protection

Updated Jun 23, 2026
Python

john-walkoe / uspto_enriched_citation_mcp

Star

High-performance MCP server for USPTO Enriched Citation API v3 with AI-powered data extraction, token-saving context reduction, progressive disclosure workflows, and seamless cross-MCP integration

Updated Jul 19, 2026
Python

imshahab / llama-sense

Star

A multi-layered prompt injection detection system built with Laravel.

laravel ai pipeline pipeline-pattern defense-in-depth huggingface-datasets llm huggingface-spaces prompt-injection prompt-injection-detector prompt-injection-defense prompt-injection-detection

Updated Dec 1, 2025
PHP

john-walkoe / courtlistener_citations_mcp

Star

MCP server for validating legal citations against CourtListener's 9M+ opinion database — detects AI-hallucinated citations, name mismatches, and ambiguous reporters with an interactive citation panel.

python legal mcp courtlistener document-analysis legal-citation security-scanning legal-tech ai-integration hallucination-detection model-context-protocol mcp-server fastmcp citation-validation legal-workflow prompt-injection-detection context-reduction court-opinions eyecite

Updated Apr 13, 2026
Python

BlackUnicornSecurity / bonklm

Star

BonkLM - LLM Security Guardrails with Interactive Setup Wizard

nodejs cli security typescript jailbreak wizard ai-safety security-tools jailbreak-detection ai-security content-moderation guardrails llm prompt-injection prompt-injection-detection

Updated Aug 18, 2026
TypeScript

john-walkoe / uspto_fpd_mcp

Star

High-performance MCP server for USPTO Final Petition Decisions API with context reduction and cross-MCP integration

Updated Jul 19, 2026
Python

john-walkoe / uspto_ptab_mcp

Star

High-performance MCP server for USPTO Patent Trial and Appeal Board (PTAB) with context reduction, progressive disclosure workflows, and seamless cross-MCP integration

Updated Jul 19, 2026
Python

smartbrainactivity / smartbrain-skill-auditor

Star

Antigravity. Claude-code. 🇬🇧 Zero-dependency Node.js CLI to statically audit third-party AI Skills for malicious code patterns before local execution. | 🇪🇸 CLI Node.js sin dependencias para auditar estáticamente Skills de IA buscando código malicioso antes de ejecutarlos.

cybersecurity ai-agents code-audit ai-security supply-chain-security cybersecurity-tools prompt-injection gemini-cli antigravity ai-skills claude-code claude-skills prompt-injection-detection antigravity-tools ai-skill gemini-cli-skills antigravity-skills skill-audit ghost-prompt

Updated Mar 11, 2026
JavaScript

john-walkoe / uspto_pfw_mcp

Star

High-performance MCP server for USPTO Patent File Wrapper API with secure document downloads, metadata access, and context reduction

python legal mcp patent document-analysis intellectual-property security-scanning legal-tech patent-documents uspto-api ai-integration model-context-protocol mcp-server fastmcp legal-workflow prompt-injection-detection patent-research context-reduction patent-file-wrapper

Updated Jul 19, 2026
Python

maxf-zn / prompt-mining

Star

Infrastructure for capturing LLM activations and SAE (Sparse Autoencoders) features, training probes for prompt maliciousness detection, and evaluating out-of-distribution generalization with Leave-One-Dataset-Out (LODO)

sparse-autoencoders out-of-distribution activation-analysis mechanistic-interpretability llm-security prompt-injection-detection activation-probing lodo-evaluation

Updated Aug 4, 2026
Python

Improve this page

Add a description, image, and links to the prompt-injection-detection topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

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

Learn more