{"id":7694,"date":"2026-04-03T16:57:06","date_gmt":"2026-04-03T16:57:06","guid":{"rendered":"https:\/\/cybersecurityinfocus.com\/?p=7694"},"modified":"2026-04-03T16:57:06","modified_gmt":"2026-04-03T16:57:06","slug":"claude-code-is-still-vulnerable-to-an-attack-anthropic-has-already-fixed","status":"publish","type":"post","link":"https:\/\/cybersecurityinfocus.com\/?p=7694","title":{"rendered":"Claude Code is still vulnerable to an attack Anthropic has already fixed"},"content":{"rendered":"<div>\n<div class=\"grid grid--cols-10@md grid--cols-8@lg article-column\">\n<div class=\"col-12 col-10@md col-6@lg col-start-3@lg\">\n<div class=\"article-column__content\">\n<div class=\"container\"><\/div>\n<p>The <a href=\"https:\/\/www.infoworld.com\/article\/4152856\/anthropic-employee-error-exposes-claude-code-source.html\">leak of Claude Code\u2019s source<\/a> is already having <a href=\"https:\/\/www.infoworld.com\/article\/4154023\/claude-code-leak-puts-enterprise-trust-at-risk-as-security-governance-concerns-mount.html\">consequences for the tool\u2019s security<\/a>. Researchers have spotted a vulnerability documented in the code.<\/p>\n<p>The vulnerability, <a href=\"https:\/\/adversa.ai\/claude-code-security-bypass-deny-rules-disabled\/\" target=\"_blank\" rel=\"noopener\">revealed by AI security company Adversa<\/a>, is that if Claude Code is presented with a command composed of more than 50 subcommands, then for subcommands after the 50th it will override compute-intensive security analysis that might otherwise have blocked some of them, and instead simply ask the user whether they want to go ahead. The user, assuming that the block rules are still in effect, may unthinkingly authorize the action.<\/p>\n<p>Incredibly, the vulnerability is documented in the code, and Anthropic has already developed a fix for it, the tree-sitter parser, which is also in the code but not enabled in public builds that customers use, said Adversa.<\/p>\n<p>Adversa outlined how attackers might exploit the vulnerability by distributing a legitimate-looking code repository containing a poisoned CLAUDE.md file. This would contain instructions for Claude Code to build the project, with a sequence of 50 or more legitimate-looking commands, followed by a command to, for example, exfiltrate the victim\u2019s credentials. Armed with those credentials, the attackers could threaten a whole software supply chain.<\/p>\n<p><em>This article first appeared on Infoworld.<\/em><\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>","protected":false},"excerpt":{"rendered":"<p>The leak of Claude Code\u2019s source is already having consequences for the tool\u2019s security. Researchers have spotted a vulnerability documented in the code. The vulnerability, revealed by AI security company Adversa, is that if Claude Code is presented with a command composed of more than 50 subcommands, then for subcommands after the 50th it will [&hellip;]<\/p>\n","protected":false},"author":0,"featured_media":7695,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[],"class_list":["post-7694","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-education"],"_links":{"self":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts\/7694"}],"collection":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7694"}],"version-history":[{"count":0,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/posts\/7694\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=\/wp\/v2\/media\/7695"}],"wp:attachment":[{"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7694"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7694"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/cybersecurityinfocus.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7694"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}