
delirium-ai-safety-benchmark
A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

PoC simulation of a critical CCSDS telecommand replay vulnerability in satellite command systems, demonstrating missing sequence-number validation…

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Windows 7 UAC Bypass Vulnerability in the Windows Script Host

Exploits the Windows Server 2025 dMSA privilege escalation vulnerability to enumerate writable OUs, escalate to arbitrary domain users, extract…

Trajectory-aware evolutionary search framework for red-teaming LLM agents over MCP servers, generating adversarial prompts to map vulnerability…

Advanced CVE-2023-44487 HTTP/2 Rapid Reset vulnerability exploitation framework. Features multi-connection concurrent attacks, adaptive rate control,…

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

Windows Defender patch bypass PoC for CVE-2026-50656 (RoguePlanet), demonstrating exploitability on Windows 11 25H2 and Server 2025 despite…

Exploit PoCs for CVE-2025-30374, a Taipy class pollution bug, demonstrating RCE, reflected XSS, DoS, and OpenAI credential leakage with Docker-based…

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,…

A prompt injection in a code‑review bot that executes AI‑generated fixes in a sandbox. The sandbox uses a blacklist to prevent dangerous commands,…

Proof-of-concept exploit for CVE-2026-73292: CSRF attack on Semaphore UI password change endpoint, serving a malicious page that silently resets an…

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

Proof-of-concept exploit for CVE-2026-44578 that reproduces the vulnerable condition, enabling security researchers to validate affected systems and…

Python PoC demonstrating CVE-2026-22020: exploitable weak seed in quantum key distribution privacy amplification, reducing final key entropy.

The poc of CVE-2026-23744