SkillSpector
nvidia/skillspectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and…
ai-securitycode-analysisdevsecops+8
23.1k
nvidia/skillspectorSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and…
jpcertcc/logontracerInvestigate malicious Windows logon by visualizing and analyzing Windows event log
graph-com/cka-agentResearch implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.
kaill-jlq/mmskillriskBenchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
stardust457/sldrDefense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
hashgraph-online/hol-guardOpen-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at…
danigil/neupermZero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…
oxydev2/clearml-cve-2024-24590Proof of concept for CVE-2024-24590
yxf203/defense-as-skillRuntime guard skill that detects and blocks malicious skill-induced attacks in skill-augmented agents, with an MCTS loop that evolves the guard…
cisco-ai-defense/skill-scannerSecurity Scanner for Agent Skills
aradhyacp/secflowAI-driven automated threat analysis pipeline that routes files, URLs, IPs, domains, or images through specialized security analyzers and generates…
gautamvarmadatla/mcpsafetywardenProxy server that wraps MCP servers with behavioral profiling, security scanning, risk gating, and safe execution. Detects prompt injection,…
db-ol/cuaharmBenchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…
shivang0/guardmodelGitHub Action that scans ML model files for malicious code and security vulnerabilities
shinthink/cve-2026-27966Pre-auth RCE scanner for Langflow < 1.8.0 — Route Injection + Vertex Injection → Code Execution (CVSS 9.8)
zhengxr930/malevalOfficial code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing
davidrxchester/cve-2026-5843Docker Container Escape POC via mlx-metal importlib