modelaudit
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
adversarial-attackai-securitydata-exfiltration+8
75
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
hydradragonantivirus/hydradragonantivirusDynamic and static analysis with Real Time Malware Analysis with Antivirus for Windows, including open-source XDR (3 EDR projects), ClamAV, YARA-X,…
promptfoo/promptfooTest your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and…
koala73/worldmonitorReal-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational…
beenuar/aisocSelf-hostable AI SOC that fuses security alerts, auto-triages via agentic AI, runs MITRE ATT&CK investigations, and logs every agent decision in a…
kevinchunye/prompt_injectionBenchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
ssrajadh/sentrysearchSemantic search over videos using Gemini Embedding 2 or Qwen3-VL.
0sec-labs/foxguardA fast universal code security scanner, written in Rust. Batteries included: supports 14 languages, TUI for triage, secrets, post-quantum audits,…
munshi007/aura-statePython framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…
deepbluedynamics/grubcrawlerThe world's fastest agentic crawler. Reclaimed. Reinvented. Ready for war.
tesseract-ocr/tesseractOpen-source OCR engine with LSTM neural network models for extracting text from images and scanned documents in 100+ languages via CLI, C/C++…
cisco-ai-defense/skill-scannerSecurity Scanner for Agent Skills
123wwwa/flownameNext-generation JavaScript identifier recovery with LLMs.
liuz233/hardeResearch code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…
iqsec-lab/freemocaMemory-free continual learning framework for malware classification using mode connectivity-based interpolation. Supports class-incremental and…
ml-security-research-lab/cachetrapResearch code for a gray-box trojan attack that flips a single KV-cache bit in fine-tuned LLM classifiers and measures per-class attack success rate.
resharma/ajarMeasuring Open Privilege in Agent Defenses