https://ai.digt.ru/en/posts/Recent content in Posts on AI Radar — ДигтHugo -- gohugo.ioru-RU© 2026 ДигтSun, 25 Oct 2026 00:00:00 +0000https://ai.digt.ru/en/posts/security-audit-skill/Sun, 25 Oct 2026 00:00:00 +0000https://ai.digt.ru/en/posts/security-audit-skill/<h1 class="relative group">Cloudflare Security Audit Skill: Verified Security Findings for AI Coding Agents <div id="cloudflare-security-audit-skill-verified-security-findings-for-ai-coding-agents" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#cloudflare-security-audit-skill-verified-security-findings-for-ai-coding-agents" aria-label="Якорь">#</a> </span> </h1> <p>Security auditing is hard to do well, and even harder to automate. Most AI coding agents can spot obvious vulnerabilities, but they struggle with multi-phase analysis, independent verification, and producing findings that downstream tools can actually consume. Cloudflare&rsquo;s <code>security-audit-skill</code> addresses this gap directly.</p> <h2 class="relative group">What It Is <div id="what-it-is" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#what-it-is" aria-label="Якорь">#</a> </span> </h2> <p><code>cloudflare/security-audit-skill</code> is a structured skill for coding agents that guides them through a rigorous, multi-phase security audit process. Instead of a single pass over the codebase, the skill breaks the audit into distinct stages: reconnaissance, threat modeling, vulnerability identification, exploitation testing, and remediation planning.</p>https://ai.digt.ru/en/posts/cindy/Sun, 25 Oct 2026 00:00:00 +0000https://ai.digt.ru/en/posts/cindy/<h1 class="relative group">Consider It Done: Meet Cindy, the Open-Source AI Agent That Works Out of the Box <div id="consider-it-done-meet-cindy-the-open-source-ai-agent-that-works-out-of-the-box" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#consider-it-done-meet-cindy-the-open-source-ai-agent-that-works-out-of-the-box" aria-label="Якорь">#</a> </span> </h1> <p>The gap between &ldquo;AI can do that&rdquo; and &ldquo;AI just did that&rdquo; is still wider than most of us would like. Cindy is an open-source AI agent designed to close that gap. Its tagline says it all: <em>想到，就能做到</em> — &ldquo;Think it, and it&rsquo;s done.&rdquo; No lengthy setup, no fragile toolchains, no secret sauce required.</p>https://ai.digt.ru/en/posts/tradingagents/Sun, 25 Oct 2026 00:00:00 +0000https://ai.digt.ru/en/posts/tradingagents/<h1 class="relative group">TradingAgents: Multi-Agent LLM Framework for Financial Trading <div id="tradingagents-multi-agent-llm-framework-for-financial-trading" class="anchor"></div> <span class="absolute top-0 w-6 transition-opacity opacity-0 -start-6 not-prose group-hover:opacity-100 select-none"> <a class="text-primary-300 dark:text-neutral-700 !no-underline" href="#tradingagents-multi-agent-llm-framework-for-financial-trading" aria-label="Якорь">#</a> </span> </h1> <p>TradingAgents is an open-source framework from TauricResearch that brings large language models into the world of financial trading through a structured multi-agent system. Instead of relying on a single model to make trading decisions, TradingAgents simulates a full trading firm where specialized agents collaborate, debate, and refine their analysis before arriving at a decision.</p>