
Security News
Re-Enabled GitHub Actions Expose Thousands of Repositories to Mini Shai-Hulud
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.
@livevariant/tools
Advanced tools
LiveVariant's tool definitions: one registry describing every operation an assistant can perform, from which the MCP server, the REST API, the OpenAPI document and the agent SKILL are all generated
LiveVariant's tool registry: one definition per operation an assistant can perform (build a test, inspect one, read results with real win probabilities), from which the MCP server, the REST API, the OpenAPI document and the agent SKILL are all generated. Embed it to expose the same tools from your own product without inheriting a transport.
Part of livevariant/livevariant; the repository README covers the whole system. AGPL-3.0.
FAQs
LiveVariant's tool definitions: one registry describing every operation an assistant can perform, from which the MCP server, the REST API, the OpenAPI document and the agent SKILL are all generated
We found that @livevariant/tools demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Two compromised GitHub Actions were re-enabled with malicious tags intact, exposing thousands of downstream repositories to Mini Shai-Hulud.

Research
/Security News
A malicious Firefox extension fetches its payload after installation to evade detection, steal Google session cookies, and automate account takeover.

Research
/Security News
The compromise affects MemTensor's MemOS, an open source memory framework for large language models (LLMs) and AI agents. Both npm package @memtensor/memos-cloud-openclaw-plugin and the PyPI package MemoryOS are compromised. They drop cross-platform Go binaries that exfiltrate developer secrets.