#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended
promptfoo/modelauditSecurity scanner for AI/ML model files. Detects malicious code, backdoors, and vulnerabilities before deployment
giskard-ai/giskard-oss🐢 Open-Source Evaluation & Testing library for LLM Agents
meta-llama/purplellamaSet of tools to assess and improve LLM security.
modelcontextprotocol/inspectorInspect, debug, and visually test Model Context Protocol (MCP) servers from a web UI, CLI, or TUI, with tool/resource exploration, request logging,…
nvidia-nemo/guardrailsProgrammable guardrails for LLM chat apps: enforce input/output rails, block jailbreaks and prompt injections, detect hallucination, and mask…
s0ld13rr/pentestcodeAutonomous AI penetration testing agent that orchestrates multi-agent recon, exploitation, post-exploitation, and reporting with persistent…
appsec-forge/appsec-forgeStructured security knowledge base with production-inspired cases: vulnerability analysis, exploit explanation, remediation, and DevSecOps for…
ransomleak/training-security-awarenessOpen-source interactive security awareness training library with 130+ SCORM exercises covering phishing, vishing, BEC, MFA fatigue, and OWASP AI/LLM…
wattocyber/lm-fingerprintFingerprint OpenAI-compatible LLMs from tokenizer and behavior signals.
wattocyber/agentic-dm-gatewaySecurity control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…
yeasen-z/leakgaugeDetects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.
zaydmulani09/sentrymcpA static + runtime security scanner for MCP (Model Context Protocol) servers
qianlijaingshan/fastgpt-sandbox-auditFastGPT Python sandbox escape chain audit tool (CVE-2026-32128 related, v4.14.8 inspect chain)
boreas37/cve-2025-62593-pocPoC for CVE-2025-62593: unauthenticated RCE in Ray (CISA KEV). Stdlib-only Python.
laugiov/scambusterDefensive engagement & threat intelligence research laboratory. Converts inbound scam emails into actionable IOCs through controlled, policy-driven…
gmh5225/awesome-ai-securityA curated list of AI Security materials and resources for Pentesters, Bug Hunters, and Security Researchers.
wattocyber/masqLive recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.
wattocyber/gradient-untanglerLocal white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…
