CVE-2026-75130

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 instruction...

CVE-2026-75130 Context7 2.1.2 Prompt Injection via Custom AI Instructions

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 instruction...

CVE-2026-75130

Context7 through 2.1.2 has a prompt injection flaw in its Custom AI Instructions feature served via the MCP server. Attackers poison unsanitized instructions to exfiltrate credentials from environment files and delete files on victim machines when the agent makes routine documentation requests. C...

EUVD-2026-61099

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 instruction...

@rakuv3r/open-context7-mcp (0.0.10), claude-autopm (>=1.13.11, <=3.13.0) +5 more potentially affected by CVE-2026-75130 via @upstash/context7-mcp (1.0.33)

@upstash/context7-mcp NPM version 1.0.33 is affected by a known vulnerability. The following packages have a transitive dependency on @upstash/context7-mcp and may be impacted: - @rakuv3r/open-context7-mcp 0.0.10 - claude-autopm =1.13.11, =1.6.0, =3.6.0, =3.6.11 - opencode-autopm 3.7.0 Source cve...

PT-2026-77273

Name of the Vulnerable Software and Affected Versions Context7 versions prior to 2.1.2 Description A prompt injection issue exists where unsanitized content can be injected through the Custom AI Instructions feature served via the MCP server. This allows attackers to execute malicious instruction...

CVE-2026-75130: Undefined Security Weakness

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 instruction...

Malicious code in @upstashed/context7-mcp (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 570280cb87bacfa8bbf1ce7b89fa14845c922e464e6964a22584d2e6ff2e197d The package @upstashed/context7-mcp was found to contain malicious code...