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

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

Evades LLM text watermarks by injecting Unicode variation selectors; includes the SynthID generator, mean-g detector, normalization defenses, and…

Security for the modern age of AI: defend against bad AI agents and malicious npm packages

AMBER ICI v5: local-first Ollama investigative command center with case-scoped evidence, agent chains, hybrid retrieval, streaming analysis, graph…

A monitoring hub that watches popular open-source repositories and uses AI to detect when commits are patching security vulnerabilities - often…

Bypass llm guardrails by confusing it with fabricated tool output.

open-source pentest management built to be operated by an AI agent

Research implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…

Technical disclosure: Credential fabrication via XML tag injection in Claude Sonnet 4.6. Reported June 14 2026, patched June 20 2026.

Automatic security vulnerability remediation for your code.

Semantic Watermarking with Order-Robust Detection over Sub-sentence Units

Curated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3…

Locally-hosted, air-gapped VAPT platform that runs 8 parallel scanning modules, deterministically scores findings with CVSS v3.1, and generates PDF…

Aurea is an open-source, AI-powered platform that secures infrastructure-as-code (IaC) across Terraform, Kubernetes, Docker, and Ansible. It…

EmailXpose is an open source AI-powered email security system that detects phishing, spam, scams, malware, and social engineering attacks. It goes…

Generation-time safety framework for LLMs that maps internal model signals to explicit rules and per-request policies, enforcing allow, refuse, or…

OWASP Top 10 for Large Language Model Applications