{"id":14169,"date":"2026-07-09T07:03:33","date_gmt":"2026-07-09T07:03:33","guid":{"rendered":"https:\/\/serisec.com\/index.php\/2026\/07\/09\/friendly-fire-ai-agents-built-to-catch-html\/"},"modified":"2026-07-09T07:03:33","modified_gmt":"2026-07-09T07:03:33","slug":"friendly-fire-ai-agents-built-to-catch-html","status":"publish","type":"post","link":"https:\/\/serisec.com\/index.php\/2026\/07\/09\/friendly-fire-ai-agents-built-to-catch-html\/","title":{"rendered":"Top\u00a0AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It"},"content":{"rendered":"<p>    Top\u00a0AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It<br \/>\n \t<BR><br \/>\n<BR><\/BR><br \/>\n    <!-- no image --><br \/>\n \t<BR><br \/>\n<BR><\/BR><\/p>\n<div>Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker&#8217;s code on your own machine instead.<\/p>\n<p>That is the finding in a\u00a0proof-of-concept published Wednesday\u00a0by the AI Now Institute, an attack it calls &#8220;Friendly Fire.&#8221; It works against Anthropic&#8217;s Claude Code and OpenAI&#8217;s Codex when either is running in an autonomous mode that approves its own<\/p><\/div>\n<p> \t<BR><br \/>\n <BR><\/BR><\/p>\n<p> \t<BR><br \/>\n<BR><\/BR><br \/>\n<a href=\"https:\/\/thehackernews.com\/2026\/07\/friendly-fire-ai-agents-built-to-catch.html\">Go to TheHackersNews<\/a><br \/>\n \t<BR><br \/>\n <BR><\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Top\u00a0AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker&#8217;s code on your own machine instead. That is the finding in a\u00a0proof-of-concept published Wednesday\u00a0by the AI Now Institute, an attack it calls &#8220;Friendly Fire.&#8221; [&hellip;]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[60],"tags":[76],"class_list":["post-14169","post","type-post","status-publish","format-standard","hentry","category-thehackersnews","tag-thehackersnews"],"_links":{"self":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/14169"}],"collection":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/comments?post=14169"}],"version-history":[{"count":0,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/posts\/14169\/revisions"}],"wp:attachment":[{"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/media?parent=14169"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/categories?post=14169"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/serisec.com\/index.php\/wp-json\/wp\/v2\/tags?post=14169"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}