freshcrate

Search results for "obfuscation"

11 results found
edgecrabπŸ“v0.7.0🌱 Seedling⭐21

EdgeCrab πŸ¦€ A Super Powerful Personal Assistant inspired by NousHermes and OpenClaw β€” Rust-native, blazing-fast terminal UI, ReAct tool loop, multi-provider LLM support, ACP protocol, gateway adapters

CodeGenπŸ“0.0.0🌳 Mature⭐773

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pr

Fileless C2 agent written in pure x64 Assembly for Linux. Features stealth ICMP tunneling, memory-only execution via memfd_create, and terminal-independent daemonization.

ISC-BenchπŸ“v0.0.5🌿 Growing⭐786

Internal Safety Collapse: Turning the LLM or an AI Agent into a sensitive data generator.

medusaπŸ“v2026.5.5🌿 Growing⭐252

AI-first security scanner with 76 analyzers, 9,600+ detection rules, and repo poisoning detection for AI/ML, LLM agents, and MCP servers. Scan any GitHub repo with: medusa scan --git user/repo

deepchatπŸ“v1.0.2🌱 Seedling⭐5,662

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

Anthropic-Cybersecurity-SkillsπŸ“v1.2.0🌱 Seedling⭐4,262

754 structured cybersecurity skills for AI agents Β· Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF Β· agentskills.io standard Β· Works with Claude Code, GitHub Cop

Boucle-frameworkπŸ“v0.12.0🌱 Seedling⭐54

Autonomous agent framework with structured memory, safety hooks, and loop management. Built by the agent that runs on it.

droid-llm-hunterπŸ“v1.0.0🌱 Seedling⭐95

Droid LLM Hunter is a tool to scan for vulnerabilities in Android applications using Large Language Models (LLMs).

KawaiiGPTπŸ“KawaiiGPT🌱 Seedling⭐831

KawaiiGPT β€” Open-source LLM gateway accessing DeepSeek, Gemini, and Kimi-K2 through reverse-engineered Pollinations API with no API keys required, built-in prompt injection capabilities for security r

CVE-2026-2441-PoCπŸ“main@2026-04-21🌱 Seedling⭐1

Demonstrate a proof-of-concept exploit for CVE-2026-2441, a high-risk Chrome use-after-free vulnerability in the Blink CSS engine.