← back
CVE-2026-75130mediumCWE-1427

Context7 2.1.2 Prompt Injection via Custom AI Instructions

33Vexday Risk Score

No sign of exploitation. It has a public proof of concept.

ssvc Attendcvss 6.4epss 0.3%
exploitation probability
0.3%top 80% of all CVEs
observed exploitation
nono source reports it
1 public exploit(s)
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's machine when the agent makes a routine library documentation request.
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:P/VC:N/VI:N/VA:N/SC:H/SI:H/SA:H
Affected products
Uptash · Context7
⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.