Critical CVSS 9
CVE-2026-75130
NVD analysis in progress
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.
What this means
- Exposure
- Exploitable remotely over the network and with an ordinary user account — but only if a user opens booby-trapped content.
- Impact
- An attacker can read sensitive data, modify or destroy data and take the service offline. The impact spreads beyond the vulnerable component into other parts of the system.
- Likelihood
- Its EPSS score stays low: nothing points to imminent exploitation, which is no reason to leave it unpatched.
What to doPatch without waiting for the next scheduled cycle.
Read automatically from the CVSS vector, the weakness type (CWE) and the EPSS score. The technical description above remains the one published by NIST.