<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Agent Security on Konda Security</title><link>https://kondasecurity.com/tags/agent-security/</link><description>Recent content in Agent Security on Konda Security</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 24 Jul 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://kondasecurity.com/tags/agent-security/index.xml" rel="self" type="application/rss+xml"/><item><title>The MCP Attack Surface: What Security Teams Are Missing</title><link>https://kondasecurity.com/blog/mcp-attack-surface-what-security-teams-miss/</link><pubDate>Fri, 24 Jul 2026 00:00:00 +0000</pubDate><guid>https://kondasecurity.com/blog/mcp-attack-surface-what-security-teams-miss/</guid><description>MCP flips a traditional security assumption — the callee can influence the caller. That&amp;rsquo;s what makes it powerful, and it&amp;rsquo;s what your security team needs to understand. A practical catalog of the attack surfaces that matter, with mitigations that don&amp;rsquo;t slow teams down.</description></item><item><title>Threat Modeling MCP: 6 Trust Boundaries Your Security Team Should Map</title><link>https://kondasecurity.com/blog/mcp-threat-model-trust-boundaries/</link><pubDate>Fri, 17 Jul 2026 00:00:00 +0000</pubDate><guid>https://kondasecurity.com/blog/mcp-threat-model-trust-boundaries/</guid><description>MCP is the right bet for connecting AI agents to enterprise tools. But deploying it well means understanding the trust boundaries. I applied STRIDE to the protocol end-to-end — here&amp;rsquo;s what to focus on so your team can move fast without getting burned.</description></item></channel></rss>