<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="../assets/feed.xsl"?><rss version="2.0"><channel><title>PatchTheCVE: praisonaiagents</title><link>https://patchthecve.com/</link><description>CVEs with upgrade or downgrade fix steps</description><item><title>CVE-2026-44339: PraisonAI is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-44339.html</link><guid>https://patchthecve.com/cve/CVE-2026-44339.html</guid><pubDate>Mon, 26 Oct 2026 18:10:00 +0000</pubDate><description>HIGH 8.6: PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.37 and praisonaiagents version 1.6.37, praisonaiagents resolves unresolved tool names against module globals and __main__ after it fails to match the declared tool list and the registry. With the default agent configuration, _pe</description></item><item><title>CVE-2026-44335: PraisonAI is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-44335.html</link><guid>https://patchthecve.com/cve/CVE-2026-44335.html</guid><pubDate>Mon, 26 Oct 2026 18:10:00 +0000</pubDate><description>CRITICAL 9.8: PraisonAI is a multi-agent teams system. Prior to version 1.6.32, the URL checking logic in PraisonAI has a logical flaw that could be bypassed by attackers, leading to SSRF attacks. This issue has been patched in version 1.6.32.</description></item><item><title>CVE-2026-41496: PraisonAI is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-41496.html</link><guid>https://patchthecve.com/cve/CVE-2026-41496.html</guid><pubDate>Mon, 26 Oct 2026 19:10:00 +0000</pubDate><description>HIGH 8.1: PraisonAI is a multi-agent teams system. Prior to praisonai version 4.6.9 and praisonaiagents version 1.6.9, the fix for CVE-2026-40315 added input validation to SQLiteConversationStore only. Nine sibling backends — MySQL, PostgreSQL, async SQLite/MySQL/PostgreSQL, Turso, SingleStore, Supabase, Surr</description></item><item><title>CVE-2026-40160: PraisonAIAgents is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-40160.html</link><guid>https://patchthecve.com/cve/CVE-2026-40160.html</guid><pubDate>Mon, 26 Oct 2026 21:10:00 +0000</pubDate><description>MEDIUM 6.5: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, web_crawl&#x27;s httpx fallback path passes user-supplied URLs directly to httpx.AsyncClient.get() with follow_redirects=True and no host validation. An LLM agent tricked into crawling an internal URL can reach cloud metadata endpoints (169</description></item><item><title>CVE-2026-40153: PraisonAIAgents is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-40153.html</link><guid>https://patchthecve.com/cve/CVE-2026-40153.html</guid><pubDate>Mon, 26 Oct 2026 21:10:00 +0000</pubDate><description>HIGH 7.4: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the execute_command function in shell_tools.py calls os.path.expandvars() on every command argument at line 64, manually re-implementing shell-level environment variable expansion despite using shell=False (line 88) for security. This </description></item><item><title>CVE-2026-40150: PraisonAIAgents is a multi-agent teams system</title><link>https://patchthecve.com/cve/CVE-2026-40150.html</link><guid>https://patchthecve.com/cve/CVE-2026-40150.html</guid><pubDate>Mon, 26 Oct 2026 21:10:00 +0000</pubDate><description>HIGH 7.7: PraisonAIAgents is a multi-agent teams system. Prior to 1.5.128, the web_crawl() function in praisonaiagents/tools/web_crawl_tools.py accepts arbitrary URLs from AI agents with zero validation. No scheme allowlisting, hostname/IP blocklisting, or private network checks are applied before fetching. T</description></item></channel></rss>