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

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…
Benchmark harness that evaluates LLM agent tool-calling security under long-horizon tasks, generating prompt-injection and tool-poisoning attacks and…

Secret-Use Delegation Protocol — protocol-level secret use for agentic systems

Steganographic prompt-injection defense for agentic AI using decode-time provenance binding, HMAC authentication, and MCP trust enforcement.

Benign, self-contained reproduction of CVE-2026-61732 (Decepticon ChatML role-boundary forgery)

OpenMed < 1.5.2 unauthenticated RCE via PII privacy-filter model loading and trust_remote_code=True

Standard-library Python security triage engine that scans web apps, APIs, LLMs, and mobile packages via passive header inspection, active canary…

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Proof-of-concept and patch for CVE-2026-57845: pickle deserialization RCE in Hugging Face datasets' pandas builder, with reproduction script and…

Unified dashboard to monitor, govern, and audit AI agents in real-time. Enforce budgets, detect policy violations, and export compliance reports for…

CybORG CAGE 2 environment updated for the paper "Alignment of Autonomous Cyber Defense Agents via Adaptive Policy Shaping"

Re-evaluating prompt-injection detectors on LLM agent tool outputs (paper draft, scripts, scores)

Research toolkit for analyzing AI agent behavioral patterns through multi-disciplinary corpus analysis. Parses session logs, runs 23 analytical…

OWASP guide defining a standardized penetration testing methodology for humanoid, industrial, and autonomous robots, covering ROS/ROS2, DDS, CAN bus,…

Analyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.

Defense framework that keeps audio-language models frozen and adds a mid-layer risk gate with late-layer safety adapters to block audio jailbreaks at…

Defense framework enforcing routed origin policy to prevent indirect prompt injection in tool-using LLM agents, with deterministic origin checks and…

Detailed disclosure of CVE-2025-67511, a command injection vulnerability in the CAI framework's SSH tool that allows AI agents to be tricked into…