<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rce on Technodrone</title><link>https://blog.technodrone.cloud/tags/rce/</link><description>Recent content in Rce on Technodrone</description><generator>Hugo</generator><language>en</language><lastBuildDate>Wed, 15 Jul 2026 07:08:00 +0300</lastBuildDate><atom:link href="https://blog.technodrone.cloud/tags/rce/index.xml" rel="self" type="application/rss+xml"/><item><title>Unexpected Code Execution: When Your Agent Becomes a Shell (ASI05)</title><link>https://blog.technodrone.cloud/2026/07/code-execution-owasp-agentic-top10.html</link><pubDate>Wed, 15 Jul 2026 07:08:00 +0300</pubDate><guid>https://blog.technodrone.cloud/2026/07/code-execution-owasp-agentic-top10.html</guid><description>&lt;p&gt;This is post #5 of the &lt;a href="https://blog.technodrone.cloud/2026/07/aws-intro-owasp-agentic-top10.html"&gt;OWASP Agentic AI Top 10: What Builders on AWS Need to Know&lt;/a&gt; series.&lt;/p&gt;
&lt;p&gt;I wrote about the trust gap with coding assistants in &lt;a href="https://blog.technodrone.cloud/2026/05/your-coding-assistant-is-not-you.html"&gt;Your Coding Assistant Is Not You&lt;/a&gt;. But when agents can both generate AND execute code without you in the loop, the stakes are even higher.&lt;/p&gt;
&lt;p&gt;You ask your coding agent to fix a failing unit test. It generates a patch, installs a dependency, runs the test suite. All good.&lt;/p&gt;</description></item></channel></rss>