https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Tue, 06 Oct 2026 06:52:24 +0000 https://cve.radiocsirt.org/vuln/euvd-2026-355501 EUVD-2026-355501 https://cve.radiocsirt.org/vuln/euvd-2026-355501 https://cve.radiocsirt.org/vuln/fkie_cve-2026-75130 <p>Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim&#39;s machine when the agent makes a routine library documentation request.</p> <p>Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim&#39;s machine when the agent makes a routine library documentation request.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2026-75130 https://cve.radiocsirt.org/vuln/ghsa-97r6-3rgm-v39r <p>Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim&#39;s machine when the agent makes a routine library documentation request.</p> <p>Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim&#39;s machine when the agent makes a routine library documentation request.</p> https://cve.radiocsirt.org/vuln/ghsa-97r6-3rgm-v39r