Category
Cybersecurity
Threat detection, fuzzing, red-team agents.
19 listings
Every Cybersecurity listing on ai-supply is a free, open-source AI capability that we scan and grade A–D for security before it appears here — so you can adopt with confidence, not just a star count. This category spans 8 Guardrails, 6 Evals, 1 Skill, 1 MCP server, 1 Dataset, 1 Pipeline and 1 Agent.
Security posture: 5 of 19 scanned rated safe · avg score 86/100.
△تقييم
Nuclei — Template-Based Vulnerability Scanner
ProjectDiscovery's fast, template-driven vulnerability scanner with 9,000+ community templates for web apps, APIs, cloud, and AI service endpoints.
ai-supply
! B · 75⟳ 22d agoguards:4
↓ 267k
◆مهارة
Trivy — Container & Supply-Chain Scanner
Aqua Security's comprehensive vulnerability scanner for containers, filesystems, Git repos, IaC, and SBOMs — now with AI/ML workload scanning.
ai-supply
! B · 88⟳ 28d agoshellinstall-hooknetwork
↓ 260k
⛨ضابط أمان
Presidio — PII Detection & Anonymization
Microsoft's open-source PII detection and anonymization engine supporting 50+ entity types across text, images, and structured data.
ai-supply
! B · 88⟳ 6d agoguards:3
↓ 172k
⛨ضابط أمان
LLM Guard — Input/Output Security Toolkit
MIT-licensed security toolkit by ProtectAI that sanitizes LLM prompts and responses — blocking prompt injection, toxic content, PII leakage, and secrets.
ai-supply
✓ A · 100⟳ 19d agoguards:7
↓ 169k
△تقييم
Prowler — Cloud Security Posture Manager
Apache-licensed multi-cloud security assessment tool covering 500+ checks across AWS, Azure, GCP, and Kubernetes, including AI service misconfigurations.
ai-supply
✓ A · 100⟳ 4d agoguards:3
↓ 165k
⛨ضابط أمان
NeMo Guardrails — Programmable LLM Safety Rails
NVIDIA's open-source toolkit for adding programmable safety, topical, and quality guardrails to LLM-based conversational systems.
ai-supply
! B · 75⟳ 27d agoguards:5
↓ 113k
△تقييم
garak — LLM Vulnerability Scanner
NVIDIA's open-source LLM vulnerability scanner that probes language models for prompt injection, jailbreaks, hallucinations, and more.
ai-supply
! B · 88⟳ 1mo agoguards:7
↓ 69k
⛨ضابط أمان
LangKit
Open-source toolkit that extracts safety and quality signals — injection, PII, toxicity, sentiment, relevance — from LLM prompts and responses.
ai-supply
! B · 75⟳ 1y agoguards:8
↓ 60k
◇خادم MCP
GhidraMCP
MCP server exposing Ghidra tools so LLMs can decompile and reverse-engineer binaries.
ai-supply
! B · 88⟳ 1y agonetwork
↓ 59k
△تقييم
PyRIT — Python Risk Identification Toolkit
Microsoft's open-source AI red-teaming toolkit for systematically finding risks in generative AI systems through automated adversarial probing.
ai-supply
✓ A · 100⟳ 4mo ago
↓ 49k
⛨ضابط أمان
Rebuff — Prompt Injection Detector
ProtectAI's self-hardening prompt-injection detector using a multi-stage defence: heuristics, LLM analysis, and a vector canary database.
ai-supply
! B · 75⟳ 2y agoguards:3
↓ 47k
▣مجموعة بيانات
In-The-Wild Jailbreak Prompts
CCS'24 dataset of 15,140 in-the-wild ChatGPT prompts including 1,405 real jailbreak prompts for training and benchmarking jailbreak detectors.
ai-supply
✓ A · 100⟳ 1y agoinjective
↓ 39k
⛨ضابط أمان
Vigil
Library and REST API that scans LLM prompts for prompt injection and jailbreaks using an ensemble of vector, transformer, YARA, and canary detectors.
ai-supply
! B · 75⟳ 2y agoguards:4
↓ 36k
⬡مسار
YARA
The pattern-matching engine for malware researchers — write rules to identify and classify malware by textual or binary signatures.
ai-supply
✓ A · 100⟳ 9mo agosecretsfs
↓ 35k
⛨ضابط أمان
Agentic Security — LLM Vulnerability Scanner
Red-teaming kit for agentic LLM workflows: 2000+ adversarial probes, RL-crafted injections, CI-ready.
ai-supply
! B · 88⟳ 1mo agoguards:6
↓ 32k
⛨ضابط أمان
ModelScan — ML Model Serialization Scanner
ProtectAI's scanner that detects malicious payloads hidden inside pickle, PyTorch, TF, and Keras model files.
ai-supply
! B · 88⟳ 5mo agoguards:3
↓ 19k
◉وكيل
Counterfit — ML Model Security Testing CLI
Microsoft Azure's CLI for adversarial robustness testing of ML models: evasion, poisoning, extraction attacks.
ai-supply
! B · 75⟳ 3y agoshellnetworkfs
↓ 17k
△تقييم
JailbreakBench
Open NeurIPS benchmark for jailbreaking LLMs: balanced harmful/benign behaviors, reproducible attack artifacts, standardized judges, and a live leaderboard.
ai-supply
! B · 75⟳ 2y agoguards:6
↓ 13k
△تقييم
HarmBench
Standardized framework for automated LLM red teaming: curated harmful behaviors plus 18+ attack methods scored by a common refusal-robustness metric.
ai-supply
! B · 75⟳ 1y agoguards:7
↓ 220