<?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/" xmlns:webfeeds="http://webfeeds.org/rss/1.0"><channel><title>Roo Code (&lt;= 3.54.0) - CraftedSignal Threat Feed</title><link>https://feed.craftedsignal.io/products/roo-code--3.54.0/</link><description>Trending threats, MITRE ATT&amp;CK coverage, and detection metadata. Fed continuously.</description><generator>Hugo</generator><language>en</language><managingEditor>hello@craftedsignal.io</managingEditor><webMaster>hello@craftedsignal.io</webMaster><lastBuildDate>Wed, 14 Oct 2026 04:36:32 +0000</lastBuildDate><atom:link href="https://feed.craftedsignal.io/products/roo-code--3.54.0/feed.xml" rel="self" type="application/rss+xml"/><image><url>https://feed.craftedsignal.io/favicon-32x32.png</url><title>CraftedSignal Threat Feed</title><link>https://feed.craftedsignal.io/</link><width>32</width><height>32</height></image><webfeeds:icon>https://feed.craftedsignal.io/favicon.svg</webfeeds:icon><item><title>Command Approval Bypass in Roo Code via Redirection</title><link>https://feed.craftedsignal.io/briefs/2026-10-roo-code-bypass/</link><pubDate>Wed, 14 Oct 2026 04:36:32 +0000</pubDate><author>hello@craftedsignal.io</author><guid isPermaLink="true">https://feed.craftedsignal.io/briefs/2026-10-roo-code-bypass/</guid><description>Roo Code through 3.54.0 contains a command approval bypass in getCommandDecision() allowing attackers to execute denied shell commands by prefixing them with a redirection operator.</description><content:encoded><![CDATA[<p>Roo Code versions 3.54.0 and earlier contain a command approval bypass vulnerability in the getCommandDecision() function. This vulnerability allows an attacker to execute denied shell commands on a developer's machine by utilizing a redirection operator (&gt;&amp;) as a prefix. The flaw stems from an insufficient validation mechanism in the allowlist logic, where an attacker can craft a payload via indirect prompt injection. By prefixing a malicious command with a redirection operator, the application incorrectly matches the input against an allowlist for a benign command (such as 'echo'), while the underlying shell proceeds to execute the intended malicious instructions. This poses a significant risk to developers using the extension in environments with sensitive access.</p>
]]></content:encoded><category domain="severity">high</category><category domain="type">advisory</category><category>supply-chain</category><category>command-execution</category><category>cve-2026-110202</category></item></channel></rss>