#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Threat intelligence brief on CVE-2026-42208, a critical pre-auth SQL injection in BerriAI LiteLLM exploited within 36 hours of disclosure. Covers…

Exploit for CVE-2026-33017, an unauthenticated RCE in Langflow 1.8.1 via the build_public_tmp endpoint, enabling Python code injection through…

Proof-of-concept demonstrating remote code execution via request-side prompt injection in OpenClaw Agent Platform, exploiting lack of integrity…

Open security research on AI coding agent infrastructure. Agent-executable remediation manifests for CVE-2026-22812 and CVE-2026-22813.

Multi-stage prompt injection technique that bypasses LLM safety alignment via identity reassignment, refusal suppression, and output coercion,…

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

Demonstrates AI agent-driven CVE remediation with cryptographic provenance tracking, showcasing detection, analysis, human approval, and verification…

Check if your AI agent setup is vulnerable to CVE-2026-33579

Research code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…

Research pipeline for detecting latent indirect prompt-injection exposure signals in agentic LLMs via hidden-state probing, including trace…

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

A Python pickling decompiler and static analyzer

Rootless container runtime and sandbox that launches kernel-enforced OCI images in milliseconds with no daemon, featuring resource profiles, seccomp…

Documents CVE-2026-52618 with a PoC for OS command injection in @webfer/mcp-ansible-drupal via executeDeployment extraVars, plus detection guidance…

Technical vulnerability analysis and proof-of-concept for CVE-2026-47630, an arbitrary dlopen via TRITON_BATCH_STRATEGY_PATH in NVIDIA Triton…

AI-powered bug bounty hunting toolkit that works with or without subscription.

An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems.

Python library for adversarial machine learning security, enabling red and blue teams to run evasion, poisoning, extraction, and inference attacks…