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: 6 of 19 scanned rated safe · avg score 86/100.

Cybersecurity leaderboard →How we grade security →Security findings →All categories →

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.

! B · 75⟳ 19d agoguards:4

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.

! B · 88⟳ 25d agoshellinstall-hooknetwork

Presidio — PII Detection & Anonymization

Microsoft's open-source PII detection and anonymization engine supporting 50+ entity types across text, images, and structured data.

✓ A · 100⟳ 27d agoguards:3

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.

✓ A · 100⟳ 17d agoguards:7

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.

✓ A · 100⟳ 8d agoguards:3

NeMo Guardrails — Programmable LLM Safety Rails

NVIDIA's open-source toolkit for adding programmable safety, topical, and quality guardrails to LLM-based conversational systems.

! B · 75⟳ 24d agoguards:5

garak — LLM Vulnerability Scanner

NVIDIA's open-source LLM vulnerability scanner that probes language models for prompt injection, jailbreaks, hallucinations, and more.

! B · 88⟳ 1mo agoguards:7

Open-source toolkit that extracts safety and quality signals — injection, PII, toxicity, sentiment, relevance — from LLM prompts and responses.

! B · 75⟳ 1y agoguards:8

MCP server exposing Ghidra tools so LLMs can decompile and reverse-engineer binaries.

! B · 88⟳ 1y agonetwork

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.

✓ A · 100⟳ 4mo ago

Rebuff — Prompt Injection Detector

ProtectAI's self-hardening prompt-injection detector using a multi-stage defence: heuristics, LLM analysis, and a vector canary database.

! B · 75⟳ 2y agoguards:3

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.

✓ A · 100⟳ 1y agoinjective

Library and REST API that scans LLM prompts for prompt injection and jailbreaks using an ensemble of vector, transformer, YARA, and canary detectors.

! B · 75⟳ 2y agoguards:4

The pattern-matching engine for malware researchers — write rules to identify and classify malware by textual or binary signatures.

✓ A · 100⟳ 8mo agosecretsfs

Agentic Security — LLM Vulnerability Scanner

Red-teaming kit for agentic LLM workflows: 2000+ adversarial probes, RL-crafted injections, CI-ready.

! B · 88⟳ 1mo agoguards:6

ModelScan — ML Model Serialization Scanner

ProtectAI's scanner that detects malicious payloads hidden inside pickle, PyTorch, TF, and Keras model files.

! B · 88⟳ 5mo agoguards:3

Counterfit — ML Model Security Testing CLI

Microsoft Azure's CLI for adversarial robustness testing of ML models: evasion, poisoning, extraction attacks.

! B · 75⟳ 3y agoshellnetworkfs

Open NeurIPS benchmark for jailbreaking LLMs: balanced harmful/benign behaviors, reproducible attack artifacts, standardized judges, and a live leaderboard.

! B · 75⟳ 2y agoguards:6

Standardized framework for automated LLM red teaming: curated harmful behaviors plus 18+ attack methods scored by a common refusal-robustness metric.

! B · 75⟳ 1y agoguards:7