
Gideon
Autonomous security operations agent for threat intelligence, vulnerability research, IOC analysis, and red teaming. Supports dual-mode operations…

Autonomous security operations agent for threat intelligence, vulnerability research, IOC analysis, and red teaming. Supports dual-mode operations…

Educational Python target range simulating CVE-2026-22807, an AI supply chain RCE via TOCTOU in model loading. Includes vulnerable library, PoC…

LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles.

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,…

Reference implementation of a multi-bit LLM watermarking scheme using coded payload spreading, unbiased reweighting, and soft-decision ECC decoding…

Professional PoC for CVE-2025-59536 and related CVEs. Demonstrates an MCP Tool Confirmation Prompt Misrepresentation in Anthropic Claude_Code leading…

A PoC for CVE-2024-3660. Arbitrary Code Execution in Keras.

🛡️ Official AI Security Tool module for CVE-2026-21858 + CVE-2025-68613 (n8n "Ni8mare" Unauthenticated Arbitrary File Read & Expression Injection…

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end…

image scaling attacks for multi-modal prompt injection

Proof of concept for CVE-2024-24590

Pre-auth RCE scanner for Langflow < 1.8.0 — Route Injection + Vertex Injection → Code Execution (CVSS 9.8)

Proof-of-concept for CVE-2026-23001: demonstrates RCE through unsafe pickle deserialization in Hugging Face Transformers by crafting a malicious…