
Security News
Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.
@sidebutton/core
Advanced tools
Core workflow engine for SideButton - YAML-based browser and shell automation.
npm install @sidebutton/core
This package provides the core workflow engine used by SideButton:
{{variable}} syntax for dynamic valuesimport { parseWorkflow, executeWorkflow } from '@sidebutton/core';
// Parse a workflow from YAML
const workflow = parseWorkflow(`
id: hello_world
title: Hello World
steps:
- type: shell.run
cmd: echo "Hello from SideButton!"
`);
// Execute the workflow
const result = await executeWorkflow(workflow, context);
| Category | Steps |
|---|---|
| Browser | navigate, click, type, scroll, hover, wait, extract, extractAll, exists, key |
| Shell | shell.run, terminal.open, terminal.run |
| LLM | llm.classify, llm.generate |
| Control | control.if, control.retry, control.stop, workflow.call |
| Data | data.first |
@sidebutton/server - MCP server with REST API and dashboardApache-2.0
FAQs

Security News
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.

Research
/Security News
Malicious Chrome and Firefox extensions target Axiom Trade and Padre users, stealing session tokens and wallet data.

Security News
GPT-6 Astra hits 100% on ExploitBench and finds zero-days autonomously, while independent tests reveal scope violations and monitoring gaps.