Tools

euph00/zoneclaw-code

Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

nishitvp/better_opts_attacks

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

imabee101/cve-2023-44487

PoC script for HTTP/2 Rapid Reset (CVE-2023-44487) that sends crafted HTTP/2 streams to trigger denial-of-service conditions on vulnerable servers,…

sisl-uri/t-backdoor

Research code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…

phkhanhtrinh23/agas

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

kuro0911/cs5446-project

Code repository for CS5446 project exploring defenses against jailbreak attacks on large-language models it includes datasets, notebooks,…

josh-blythe/bordair-detector

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

protectai/llm-guard

The Security Toolkit for LLM Interactions

rosesecurity/anti-virus-evading-payloads

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

ezramansor/cve-2025-32432-poc

A simple PoC on the Remote Code Execution (RCE) Vulnerability of CraftCMS designated as CVE-2025-32432 written in Go

choisg/onedriveupdatersideloading

Payload for DLL sideloading of the OneDriveUpdater.exe, based on the PaloAltoNetwork Unit42's blog post

atsukisato/pgm-attack

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

ml-security-research-lab/cachetrap

Research 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.

d419h/iconjector

Inject DLLs into the explorer process using icons

yeasen-z/leakgauge

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

wang-yanting/agentwatcher

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

gmh5225/bedaisy-bypass

Kernel-mode hook that intercepts, decrypts, and nullifies BEDaisy-to-service report traffic to suppress anti-cheat detection on UEFI and non-UEFI…