Tag
This article introduces claude-browser-stack and agent-pods, a tool that automates browser development loops by enabling AI agents to debug APIs, scan for vulnerabilities, record user flows, and provide visual context to Claude, closing the loop between coding and verification.
AI-based security scanning has discovered 17 bugs in Perfetto's trace processor over 10 weeks, highlighting the potential for AI to uncover vulnerabilities in long-tail code that previously received little attention.
The article warns that the MCP ecosystem is repeating the same supply chain security pattern seen in npm, Docker, and PyPI, with minimal vetting and growing risks. It highlights that a scan of 500 Smithery servers found 18.8% with security issues and that existing security tooling cannot handle malicious agent instructions, and introduces a new static scanner called bawbel.
HermesHub is a curated skills registry for Hermes Agent by Nous Research, enabling installation and sharing of verified skills with automated security scanning and a creator marketplace.