<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0">
    <channel>
        <title><![CDATA[Anshuman Bhartiya]]></title>
        <description><![CDATA[Anshuman Bhartiya - Staff Security Engineer, AppSec Tech Lead, and co-host of The Boring AppSec Podcast.]]></description>
        <link>https://www.anshuman.ai</link>
        <image>
            <url>https://www.anshuman.ai/images/profile.jpg</url>
            <title>Anshuman Bhartiya</title>
            <link>https://www.anshuman.ai</link>
        </image>
        <generator>RSS for Node</generator>
        <lastBuildDate>Wed, 16 Sep 2026 14:49:36 GMT</lastBuildDate>
        <atom:link href="https://www.anshuman.ai/api/rss" rel="self" type="application/rss+xml"/>
        <language><![CDATA[en]]></language>
        <item>
            <title><![CDATA[Building a Real-World Security Benchmark for AI Code Scanners]]></title>
            <description><![CDATA[How do you know if your AI security scanner actually works? Not on toy apps. Not on intentionally vulnerable code where every bug is planted like an Easter…]]></description>
            <link>https://www.anshuman.ai/posts/openclaw-advisory-benchmark</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/openclaw-advisory-benchmark</guid>
            <pubDate>Fri, 27 Mar 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[VulnVibes: Building an AI Agent That Reasons Across Microservices to Find Real Vulnerabilities]]></title>
            <description><![CDATA[Picture this: you're reviewing a pull request. A developer on your team has added a new API endpoint that fetches content from a URL the user provides. There's…]]></description>
            <link>https://www.anshuman.ai/posts/vulnvibes-intro</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/vulnvibes-intro</guid>
            <pubDate>Fri, 13 Mar 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Day in the Life: Building a Prototype with My AI Agent (Without Getting Pwned)]]></title>
            <description><![CDATA[Series: Building with Sage — This is Part 1 of an ongoing series about running a personal AI agent with a security-first mindset. I'll share real workflows…]]></description>
            <link>https://www.anshuman.ai/posts/building-with-sage-1</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/building-with-sage-1</guid>
            <pubDate>Fri, 13 Feb 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Browser Relay: When Your AI Assistant Gets Hands on Your Browser]]></title>
            <description><![CDATA[I am sure you have felt it — the relentless firehose of information. X (formerly Twitter) has become ground zero for AI and tech announcements. LinkedIn?…]]></description>
            <link>https://www.anshuman.ai/posts/browser-relay</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/browser-relay</guid>
            <pubDate>Sun, 25 Jan 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Skills: The Missing Piece in AI Security Tooling]]></title>
            <description><![CDATA[Building on the SecureVibes series — this post explores how skills transform generic AI agents into domain experts. Here's a pattern I've seen across the…]]></description>
            <link>https://www.anshuman.ai/posts/securevibes-part4</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/securevibes-part4</guid>
            <pubDate>Sat, 17 Jan 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How I Prompted My Personal AI Assistant to Write a Blog For Me]]></title>
            <description><![CDATA[Earlier today I published a comprehensive blog post about my Clawdbot setup. It covered Docker deployment, multi-channel configuration, AI model selection…]]></description>
            <link>https://www.anshuman.ai/posts/blogging-from-telegram</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/blogging-from-telegram</guid>
            <pubDate>Fri, 16 Jan 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Introducing Sage: My Personal AI Assistant That Actually Works]]></title>
            <description><![CDATA[I've been on a quest for the perfect personal AI assistant for a while now. Not the kind that lives in a web browser tab that I have to actively go to, but…]]></description>
            <link>https://www.anshuman.ai/posts/my-clawdbot-setup</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/my-clawdbot-setup</guid>
            <pubDate>Thu, 15 Jan 2026 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Running SecureVibes on SecureVibes - Results & What's Next (Part 3/3)]]></title>
            <description><![CDATA[This is Part 3 of a 3-part series on building SecureVibes, a multi-agent security system for vibecoded applications. Series Navigation: Part 1 | Part 2 | Part…]]></description>
            <link>https://www.anshuman.ai/posts/securevibes-part3</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/securevibes-part3</guid>
            <pubDate>Tue, 14 Oct 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Building SecureVibes: A Multi-Agent Security System (Part 2/3)]]></title>
            <description><![CDATA[This is Part 2 of a 3-part series on building SecureVibes, a multi-agent security system for vibecoded applications. Series Navigation: Part 1 | Part 2 | Part…]]></description>
            <link>https://www.anshuman.ai/posts/securevibes-part2</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/securevibes-part2</guid>
            <pubDate>Tue, 14 Oct 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[The Vibecoding Security Crisis: Why Current Scanners Fail (Part 1/3)]]></title>
            <description><![CDATA[This is Part 1 of a 3-part series on building SecureVibes, a multi-agent security system for vibecoded applications. Series Navigation: Part 1 | Part 2 | Part…]]></description>
            <link>https://www.anshuman.ai/posts/securevibes-part1</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/securevibes-part1</guid>
            <pubDate>Tue, 14 Oct 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Introducing SecureVibes: A Multi-Agent Security System (3 Part Series)]]></title>
            <description><![CDATA[I built SecureVibes, an open-source multi-agent security system, that can help find security vulnerabilities in your vibecoded applications (and hopefully soon…]]></description>
            <link>https://www.anshuman.ai/posts/securevibes-intro</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/securevibes-intro</guid>
            <pubDate>Tue, 14 Oct 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How to build a defensive AI security agent with RAG]]></title>
            <description><![CDATA[In my previous post, I walked through a POC of building an offensive AI security agent, where that agent was able to analyze malicious javascript files and…]]></description>
            <link>https://www.anshuman.ai/posts/defenseagent</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/defenseagent</guid>
            <pubDate>Fri, 03 Jan 2025 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[How to build an offensive AI security agent]]></title>
            <description><![CDATA[A few weeks ago, I wrote about how LLMs could potentially disrupt the Application Security space. You can find that blog post here - The Future of Application…]]></description>
            <link>https://www.anshuman.ai/posts/hackagent</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/hackagent</guid>
            <pubDate>Fri, 13 Dec 2024 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[The Future of Application Security: Integrating LLMs and AI Agents into Manual Workflows]]></title>
            <description><![CDATA[The responsibility of an application security team in any organization has traditionally been to reduce risk. They do that by identifying and remediating…]]></description>
            <link>https://www.anshuman.ai/posts/the-future-of-appsec</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/the-future-of-appsec</guid>
            <pubDate>Wed, 23 Oct 2024 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[A Guide To Identify Authorization Vulnerabilities At Scale Using Semgrep]]></title>
            <description><![CDATA[Authorization (henceforth referred to as AuthZ) vulnerabilities such as Horizontal Privilege Escalation, Vertical Privilege Escalation, Insecure Direct Object…]]></description>
            <link>https://www.anshuman.ai/posts/detect-authz-at-scale-nestjs</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/detect-authz-at-scale-nestjs</guid>
            <pubDate>Wed, 05 Oct 2022 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[A Guide On Implementing An Effective SAST Workflow]]></title>
            <description><![CDATA[In the previous post, I wrote about implementing a lightweight Secure SDLC program using the crawl/walk/run approach. In the crawl phase, I covered activities…]]></description>
            <link>https://www.anshuman.ai/posts/sast-workflow</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/sast-workflow</guid>
            <pubDate>Thu, 18 Aug 2022 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[A Lightweight Approach To Implement Secure Software Development LifeCycle (Secure SDLC)]]></title>
            <description><![CDATA[Secure SDLC is an integral part of any Product Security program. It enables organizations to be successful in their ProdSec maturity journey. In this post, I…]]></description>
            <link>https://www.anshuman.ai/posts/secure-sdlc</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/secure-sdlc</guid>
            <pubDate>Fri, 12 Aug 2022 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Product Security Roadmap]]></title>
            <description><![CDATA[If you haven't seen it already, I wrote about some basic fundamentals to consider when building a Product Security program in an organization - Building a…]]></description>
            <link>https://www.anshuman.ai/posts/prodsec-roadmap</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/prodsec-roadmap</guid>
            <pubDate>Fri, 05 Aug 2022 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Building a Product Security program from scratch]]></title>
            <description><![CDATA[Hi! This is my attempt to reinvigorate this blog by sharing my experiences of building security programs from scratch (more specifically Product/Application…]]></description>
            <link>https://www.anshuman.ai/posts/building-product-security-program</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/building-product-security-program</guid>
            <pubDate>Mon, 25 Jul 2022 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Ability to send payment requests inspite of being blocked by the recipient]]></title>
            <description><![CDATA[TL;DR - I, as an attacker could send payment requests to anyone on Facebook even if: I am not a friend of the victim recipient The victim recipient has…]]></description>
            <link>https://www.anshuman.ai/posts/send-payment-blocked-by-recipient</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/send-payment-blocked-by-recipient</guid>
            <pubDate>Mon, 08 Feb 2016 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[A CSRF protection bypass technique]]></title>
            <description><![CDATA[This technique can be used to bypass CSRF protections in some applications by using a static CSRF token (for all users of that application) that looks like a…]]></description>
            <link>https://www.anshuman.ai/posts/csrf-protection-bypass-technique</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/csrf-protection-bypass-technique</guid>
            <pubDate>Thu, 30 Apr 2015 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[A bug in Facebook that violated my privacy]]></title>
            <description><![CDATA[The bug that I am going to describe here was actually discovered accidentally while I was checking my privacy settings in Facebook. And, it is so simple that…]]></description>
            <link>https://www.anshuman.ai/posts/facebook-privacy-bug</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/facebook-privacy-bug</guid>
            <pubDate>Tue, 23 Dec 2014 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Analysis of the BrowserStack breach - A classic example of "Pivoting in the Clouds"]]></title>
            <description><![CDATA[BrowserStack was recently breached and it was all over the news as is the case with almost all breaches these days. In this blog post, I will briefly describe…]]></description>
            <link>https://www.anshuman.ai/posts/analysis-of-browserstack-breach</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/analysis-of-browserstack-breach</guid>
            <pubDate>Thu, 13 Nov 2014 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Security issues with friction-less signup flows]]></title>
            <description><![CDATA[I believe this issue affects a lot of applications that have friction-less signup flows i.e. creating accounts without first confirming it via email. This can…]]></description>
            <link>https://www.anshuman.ai/posts/security-issues-with-friction-less-signup-flows</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/security-issues-with-friction-less-signup-flows</guid>
            <pubDate>Wed, 16 Jul 2014 00:00:00 GMT</pubDate>
        </item>
        <item>
            <title><![CDATA[Performing code review on shell scripts]]></title>
            <description><![CDATA[Check if the scripts are using absolute or relative paths. Using absolute paths wherever possible is recommended as a good practice. Check all input/output.…]]></description>
            <link>https://www.anshuman.ai/posts/performing-code-review-on-shell-scripts</link>
            <guid isPermaLink="false">https://www.anshuman.ai/posts/performing-code-review-on-shell-scripts</guid>
            <pubDate>Thu, 26 Sep 2013 00:00:00 GMT</pubDate>
        </item>
    </channel>
</rss>