
AiSOC
Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…

Open-source AI-powered Security Operations Center — alert fusion, purple-team drills, agent-assisted triage, MITRE ATT&CK investigation.…

First public analysis of SoftLanding UEFI bootkit: Ring -2 implant, CVE-2025-7029, 240+ Gigabyte boards, GPU AI evasion, dual C2. YARA + Sigma +…

Forensic toolkit and agent skills for investigating Rails Active Storage/libvips CVE-2026-66066: detects crafted blob indicators, exposure windows,…

Curated repository of threat intelligence feeds, IoC lists, YARA rules, and DFIR tool references for SOC/CERT/CTI detection and incident response.

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.

OpsGuard eliminates the "3 AM PagerDuty" nightmare, specifically protecting against threats like the recent CVE-2025-55184 (Next.js DoS)

A Java Agent that disables Apache Log4J's JNDI Lookup to mitigate CVE-2021-44228 ("Log4Shell").

A mitigation for CVE-2021-44228 (log4shell) that works by patching the vulnerability at runtime. (Works with any vulnerable java software, tested…

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)

Asymmetric defense against adversarial AI agents. VeilGate evaluates each incoming request, redirects suspected agents into a per-IP-consistent…

eBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via…

817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3…

Research and analysis of the ServiceNow Virtual Agent vulnerability (CVE-2025-12420), including attack flow, MITRE ATT&CK mapping, detection…

Find and redact secrets in AI coding agent histories (Claude Code, and more).

EDRUnChoker - fileless WMI defense that removes EDRChoker QoS throttling policies

A security-first MCP server that empowers AI agents to perform automated reverse engineering, malware analysis, forensics, vulnerability research,…

Lightweight macOS detection agent built on Santa’s Endpoint Security telemetry.