simoesctt/ctt-serverless-rce-v1.0---convergent-time-theory-enhanced-mcp-exploitServerless Framework MCP Server (CVE-2025-69256) Base Score: 9.4/10 → CTT Enhanced Score: 9.9/10 A critical command injection vulnerability in…
funnywolf/viperAdversary simulation and Red teaming platform with AI
tihanyin/pssw100avbA list of useful Powershell scripts with 100% AV bypass (At the time of publication).
owasp/aisvsThe AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…
safety-research/bloomAutomated behavioral evaluation framework for LLMs that generates diverse test scenarios to probe for sycophancy, bias, and other safety-relevant…
adityabhatt3010/cve-2025-54794-hijacking-claude-ai-with-a-prompt-injection-the-jailbreak-that-talked-backA high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…
leviticus-triage/cerebro-red-v2CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation
zjuicsr/deeptrapSecurity benchmark for evaluating OpenClaw agents against adversarial execution contexts including poisoned files, injected skills, misleading tool…
xuyw-seu/packetpatchPractical black-box adversarial packet generation against encrypted traffic classification with minimal overhead and full packet recoverability.
canonicalmg/reverse-captcha-evalEvaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in normal-looking text, with…
josh-blythe/bordair-detectorTwo-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…
cognitive-functors/c4-meta-systemProduction AI defense with 7-layer protection: mathematical constraints, object-capability access, distributed O2 consensus, SVETILO ethics. First…
0tsystemspublicrepos/ifritproxyIFRIT is an AI-powered reverse proxy that intercepts incoming requests in real time, classifying each one as legitimate or malicious. Legitimate…
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
p-e-w/hereticFully automatic censorship removal for language models
ottosulin/awesome-ai-securityA collection of awesome resources related AI security
meridianlabs-ai/inspect_petriAn alignment auditing agent capable of quickly exploring alignment hypothesis
cchio/deep-pwningMetasploit for machine learning.
