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

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

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

An Open Harness and Benchmark for AI in Cybersecurity Operations.

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

8 Lessons, Kick-start Your Cybersecurity Learning.


LLM-driven generator for Mythic Agents, Payload-Type and C2 Profiles.

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

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

Local white-box gradient attacks for open-weight LLMs: GCG/PEZ suffix search, layer saliency, weight snapshots, and rank-1 suffix-to-delta fitting…

Fingerprint OpenAI-compatible LLMs from tokenizer and behavior signals.

Live recon and posture auditing for AI agent infrastructure: scans MCP configs, session logs, and APIs for secrets, poisoned catalogs, and CoT leaks.

Cybersecurity AI (CAI), the framework for AI Security

Security control plane for LLM agents: allowlists, owner kill switch, PIN sessions, rate limits, prompt-injection detection, and output scrubbing to…

A contextual security auditing system for research artifacts

Structured security knowledge base with production-inspired cases: vulnerability analysis, exploit explanation, remediation, and DevSecOps for…

Proof-of-concept exploit for CVE-2026-33017, an unauthenticated RCE in Langflow's build_public_tmp endpoint, injecting a malicious custom component…

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.