the problem isn’t OpenClaw. it’s the architecture.

kept by eddie feb 16

The article argues that the security risks from AI agent frameworks like OpenClaw are inherent to the architecture of autonomous tool use and marketplaces, not just a single platform.

GitHub - KeygraphHQ/shannon: Fully autonomous AI hacker to find actual exploits in your web apps. Shannon has achieved a 96.15% success rate on the hint-free, source-aware XBOW Benchmark.
Shannon is an autonomous AI pentester that analyzes source code and executes real exploits to prove vulnerabilities, achieving a 96.15% success rate on the XBOW benchmark.
also on OWASP, #security, Anthropic, #open-source
A GitHub Issue Title Compromised 4,000 Developer Machines
A prompt injection in a GitHub issue title tricked an AI triage bot into executing code, enabling cache poisoning, credential theft, and publication of a compromised Cline npm package that silently installed the OpenClaw AI agent on 4,000 developer machines.
also on #supply-chain, OpenClaw, #security, Anthropic, #ai-agents
Anthropic invests $1.5M in the Python Software Foundation
Anthropic donated $1.5 million over two years to the Python Software Foundation, earmarked primarily for improving Python ecosystem security and supply-chain protection.
also on #supply-chain, #security, Anthropic, #open-source
the browser is the sandbox
The browser's 30-year-old sandbox model can be adapted to safely run AI agents locally, though gaps remain in network isolation and malicious file creation.
also on Simon Willison, #security, Anthropic, #ai-agents
LLM predictions for 2026, shared with Oxide and Friends
Simon Willison predicts LLMs will write undeniably good code in 2026, sandboxing will be solved, and a coding agent security disaster is imminent.
also on Simon Willison, #security