#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
centisgood/duo-agentflow-auditorAI Code Security — four agents that catch what SAST misses in AI-generated code. Built on GitLab Duo Agent Platform.
skrkcb2/cve-2024-5452Detailed technical analysis of CVE-2024-5452, a remote code execution vulnerability in PyTorch Lightning via DeepDiff delta property pollution, with…
gothburz/cve-2024-11040vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks.
soildworks/agentic-clip-benchmarkAn automated, high-precision zero-shot evaluation pipeline for OpenAI's CLIP model on CIFAR-10. Features 88.80% accuracy, Safetensors security…
dannz1337/deep-reaverAI-enhanced vulnerability assessment and exploitation toolkit for modular scanning of web applications, detecting SQLi, XSS, RCE, CSRF, and more with…
hh-hunter/ml-cve-2023-1177Machine learning-based exploit for CVE-2023-1177 vulnerability, enabling automated security testing and exploitation of the identified flaw.
imthecopilotnow/cve-2025-492025Detailed security advisory for CVE-2025-492025, documenting a UI misrepresentation vulnerability in Copilot AI that injects unintended hyperlinks…
soemoescode/guardskillRead-only scanner for git settings that let a repository run code in coding agents (Claude Code, Codex, Cursor, Copilot). Covers the GitSpawn class…
safeagent-beihang/clawguardEnterprise AI agent security toolkit providing pre-flight auditing, configuration hardening, runtime threat detection, and active defense against…
asteroid-belt/skultoOffline and security-first tool for syncing and managing agent skills
aipentest/cyberstrikeaiThe system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…
geeksikhsecurity/ai-tool-poisoning-guardFree security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…
pvharmo2/gha-lab-733c168b88Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into…
n0qword/mythic_ornnLLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles.
pigeonlabshq/pigeonEnforce least-privilege delegation for AI agents with signed, scoped credentials. Grant sub-agents narrow capabilities and resources, verify actions…
iamavu/zairoScans code diffs with context to build an impact graph and uses LLMs to find vulnerabilities, supporting multi-repo scans and CI gating with SARIF…
fknmega/aetherAutonomous AI Driven OSINT & security-research desktop agent (macOS/Windows) that builds a live knowledge graph. Authorized use only
mouteee/autonomous-offensive-llm-handbookA deterministic harness and handbook for autonomous offensive LLM agents, enforcing authorization, scope, and evidence gates to ensure reproducible…
