
refusal-relocates
Refusal localizes, the damage relocates, safety layers under few-sample fine-tuning
Short editorial updates from published cybersecurity tools.

Refusal localizes, the damage relocates, safety layers under few-sample fine-tuning

A high-fidelity, read-only internal network security assessment toolkit for Linux and Windows infrastructure. Employs a zero-mutation, default-deny…

Main repo for hosting release binaries

Open-source gateway that secures, governs, and observes AI agents' MCP tool calls and LLM traffic, with API-key authentication and an admin console…

A Windows runtime analysis toolkit combining memory scanning, debugging, automation, and AI-friendly APIs.

Python/Go framework that generates SQL injection PoC requests, automates sqlmap attacks, and manages modular exploit scripts with parameter detection…

Automate browser based workflows with AI

Open-source XDR and SIEM platform for threat detection, log analysis, file integrity monitoring, vulnerability assessment, and compliance management…

Scans Kubernetes clusters from any identity, flags dangerous permissions, and chains them into multi-step escalation paths to cluster compromise.

Content-blind reverse proxy for exposure-protected security scanning

Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more

Research code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…