Maxime Coquerel

Ready for #KCDToronto! 🤩 #CNCF

Three LLMs review your design plan in parallel — paste 30 lines into your CLAUDE.md, no install needed. github.com/permoon/multi-…

🐜 OpenAnt — AI-Powered Vulnerability Discovery Tool An open-source LLM-based security scanner that detects and verifies real vulnerabilities with fewer false positives. ⚡ Stage 1 detects → Stage 2 attacks → verified findings only ⚡ Supports Go, Python, JS/TS, C/C++, PHP & Ruby ⚡ Built for defenders & OSS maintainers ⚡ Claude Opus powered analysis pipeline ⚡ Apache 2.0 licensed A serious project for AI-assisted AppSec & vuln research. github.com/knostic/OpenAnt #AppSec #CyberSecurity #AI #OpenSource #BugBounty

On my way to #KCDToronto! 🚀 Excited to connect with the cloud native community and talk Kubernetes security at #KCD #CNCF

Simulates LLM attacks locally with 50+ vulnerabilities github.com/confident-ai/d…

One month to go until the next public edition of my Entra ID course in The Hague. Working on some roadrecon and roadtx updates from my backlog, and new content on agent identities! Tickets are still available via events.outsidersecurity.nl/entra-26-07/

Kubernetes v1.36: Admission Policies That Can't Be Deleted - kubernetes.io/blog/2026/05/0… #Kubernetes

CrabTrap : un proxy HTTP qui s'intercale entre vos agents IA et les APIs externes, évalue chaque requête sortante via des règles statiques + un LLM judge, et bloque ce qui ne correspond pas à votre politique de sécurité. github.com/brexhq/CrabTrap

AI-Powered Agents for Bub-Bounty Pentesting and Red-Teaming purposes github.com/matty69v/Bug-B…

How I Found Open-Source 0-days with an LLM Multi-Agent Workflow - Hyunseo Shin blog.cykor.kr/2026/02/How-I-…

CVE-2026-3865: CSI Driver for SMB path traversal via subDir may delete unintended directories on the SMB server - github.com/kubernetes/kub…

Open source is eating AI #OSFF2026

FINOS Ecosystem! #OSFF2026

Ready for #OSFF2026 ! 🤩

Another blow to Anthropic! Devs built a free and better Claude alternative that: - runs locally - works with any LLM - beats it on deep research - has Cowork-like capabilities - connects to 40+ data sources - self-hosts via Docker, and more. 100% open-source (20k+ stars).

Azure-AppHunter: Azure AppHunter is an open-source tool created for security researchers, red teamers and defenders to help them identify excessive privileges assigned to Service Principals #cloudsecurity #azuresecurity github.com/8ales/Azure-Ap…

OpenShell is the safe, private runtime for autonomous AI agents. github.com/NVIDIA/OpenShe…

Collection of papers on LLM for vulnerability detection github.com/huhusmang/Awes… #llm #infosec

Software distribution platform for AI companies with minimal setup github.com/distr-sh/distr