
openclaw-technical-analysis
This technical research and review is for educational purposes on public code and constitutes Fair Dealing under the Copyright Act (Canada).

This technical research and review is for educational purposes on public code and constitutes Fair Dealing under the Copyright Act (Canada).

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

Benchmark and defense code for persistent memory attacks on OpenClaw-style computer-use agents, with memory-zoning mitigation, attack scenarios, and…

Research code and dataset (WSD) for evaluating audio watermarking impact on anti-spoofing, using wav2vec2 XLS-R and knowledge-preserving learning.

Your personal AI assistant at all-in 888KiB (~35KB in app code). Running on an ESP32. GPIO, cron, custom tools, memory, and more.

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

Benchmark suite and code for detecting AI alignment failures, with 44 benchmarks across ten failure types and a zero-shot RLCD detector evaluated on…

A collection of challenge based hack-a-thons including student guide, coach guide, lecture presentations, sample/instructional code and templates. …

Embeds and detects keyed, style-based watermarks in LLM-generated Python, Java, and C++ code via CST rewriting, preserving functional correctness and…

AI-native code security auditor on AgentField that proves exploitability with verdicts, traces, and actionable evidence.

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

AI-powered MCP server for Flipper Zero. Control SubGHz, NFC, RFID, IR, BLE, GPIO, and more over WiFi using Claude or any MCP client.

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run,…

AST-based Static Code Analyzer with Agentic LLM-Powered Relationship Mapping to discover Python RCE paths and deep deserialization chains on AI, LLM,…

Research code implementing T-Backdoor, temporal-trigger backdoor attacks on spiking neural networks using rate, latency, and jitter triggers without…

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.