Tag
Explore by tags
Enforces filesystem and network limits on arbitrary processes at the OS level, no container required. Uses macOS Seatbelt, Linux bubblewrap, and the Windows Filtering Platform; built to sandbox MCP servers and AI agents under a secure-by-default model.
Drives penetration testing from chat commands, orchestrating 100+ security tools through an MCP-native multi-agent engine on CloudWeGo Eino. Adds attack-chain graphs, risk scoring, and human-in-the-loop approval gates for authorized use.
Curated collection of 70 hands‑on cybersecurity projects, certification roadmaps and learning resources organized into Foundations/Beginner/Intermediate/Advanced tiers. Each project ships source code plus deep learn/ documentation; several focus on AI security (LLM prompt defenses, ML threat detection).
Provides an in‑IDE interface for IntelliJ IDEA to interact with Anthropic Claude Code and OpenAI Codex for AI-assisted coding. Supports dual-engine switching, file-aware context, session history, agent skills, MCP extensions, and security/permission controls.
Detects and surgically removes Google's SynthID watermark from images using multi-resolution spectral analysis and a resolution-aware codebook; provides a V3 bypass with high PSNR and strong phase-coherence reduction. Research-focused and intended for analysis/defense, not misrepresentation.
Runs untrusted AI-agent code, commands, and file operations inside isolated sandboxes that scale from local Docker to Kubernetes. One Sandbox Protocol unifies both runtimes, with gVisor, Kata, and Firecracker isolation and SDKs across five languages.
Defines a standardized commerce protocol so platforms, merchants, PSPs and credential providers can declare capabilities, discover services, manage checkouts, exchange payment tokens, and enable AI agents to perform end-to-end purchase flows.
Intercepts and blocks destructive git, filesystem and CLI commands before they execute when run by AI coding agents. Offers sub-millisecond hook latency, 50+ modular rule packs, heredoc/inline-script AST scanning, agent-specific integrations and configurable bypass/allow-once workflows.
Provides a comprehensive, security-first guide and template library for using Claude Code — from core concepts and agentic workflows to production hardening. Includes threat DB (CVE mappings), 219 templates, 271-question quiz, and interactive diagrams.
Provides a framework to build, evaluate, and run AI SRE agents that investigate and remediate production incidents on your infrastructure. Includes a CLI, synthetic + end-to-end benchmark suites, and 40+ connectors for observability, infra, and LLM providers so teams can train agents and run investigations locally or in cloud.
Provides a Claude Code plugin marketplace that supplies modular skills for security research, vulnerability detection, and audit workflows. Includes scanners, analysis skills, and developer tooling to embed LLM-assisted security checks into existing pipelines.