Tools

aniketkarne/aco-prompt-shield

Stop prompt injection attacks before they reach your LLM — zero API costs, runs entirely locally, integrates in 2 minutes. Prompt injection is the…

shaheeryasirofficial/smugglemypayload

Generates HTML smuggling pages that embed and reconstruct files client-side via JavaScript, with payload encoding, chunking, obfuscation, and…

deep-jlu/skillpoison

Research pipeline that constructs verified successful experiences and organizes them into formation records to progressively poison model skills via…

abhinavdubey30/perturbed-embedding-vectors

Code, response logs and labels for the paper Jailbreaking Open-Weight LLMs via Random Embedding Perturbations

zju-llm-safety/darwin

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

alex66366/odpure

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

pppyb/secopd

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

hunt-benito/the-sanitizer-is-the-weapon-cve-2026-68749-cve-2026-68750-quadratic-dos-in-elixir-html-sanitize-ex

PoC demonstrating quadratic DoS in Elixir html_sanitize_ex via crafted HTML; includes timing benchmarks, remote exploitation curl, and verification…

george0papasotiriou/cve-2026-23003-cross-chain-bridge-message-forging-via-missing-origin-chain-id

Cross-chain bridge PoC for CVE-2026-23003: demonstrates message forging via missing origin chain ID using vulnerable Solidity contract and Python…

george0papasotiriou/cve-2026-22016-ipfs-cid-spoofing-via-multihash-length-extension

Python proof-of-concept demonstrating IPFS CID spoofing via multihash length extension, highlighting content-addressing verification flaws that can…

george0papasotiriou/cve-2026-22003-redis-lua-sandbox-escape-via-debug.sethook-

Proof-of-concept exploit for CVE-2026-22003 demonstrating Redis Lua sandbox escape via debug.sethook to execute arbitrary system commands.

george0papasotiriou/cve-2026-21016-malicious-pypi-package-install-hook-setup.py-execution-

Demonstrates how a malicious Python package executes arbitrary commands during pip install via setup.py, highlighting PyPI supply chain and…

george0papasotiriou/cve-2026-0101-ble-address-spoofing-via-weak-resolvable-private-address

Python PoC for CVE-2026-0101 demonstrating BLE address spoofing via replay of a captured Resolvable Private Address to impersonate a trusted…

george0papasotiriou/cve-2026-7070-rdp-clipboard-hijacking-via-virtual-channel-injection

CVE-2026-7070 PoC for RDP clipboard hijacking via virtual channel injection; includes simulated server and exploit script for data theft/credential…

george0papasotiriou/cve-2026-5556-kubernetes-admission-controller-bypass-via-case-sensitivity

Exploit PoC and vulnerable admission webhook for CVE-2026-5556, demonstrating Kubernetes admission controller bypass via case-sensitive pod name…

secdev02/easytokens

Kali365 - EvilTokens Replica

hanxi19/black_hole_attack_for_vector_database

Research implementation of the Black-Hole Attack that poisons vector database indexes via centrality-driven hubness, with FAISS pipelines and…