Uptash Context7 up to 2.1.2 Custom AI Instructions injection

Summaryinfo

A vulnerability described as critical has been identified in Uptash Context7 up to 2.1.2. This vulnerability affects unknown code of the component Custom AI Instructions. Executing a manipulation can lead to injection. This vulnerability is registered as CVE-2026-75130. It is possible to launch the attack remotely. No exploit is available.

Detailsinfo

A vulnerability has been found in Uptash Context7 up to 2.1.2 and classified as critical. This vulnerability affects an unknown code block of the component Custom AI Instructions. The manipulation with an unknown input leads to a injection vulnerability. The CWE definition for the vulnerability is CWE-74. The product constructs all or part of a command, data structure, or record using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify how it is parsed or interpreted when it is sent to a downstream component. As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is shared for download at noma.security. This vulnerability was named CVE-2026-75130 since 08/17/2026. The exploitation appears to be easy. The attack can be initiated remotely. Successful exploitation requires user interaction by the victim. There are neither technical details nor an exploit publicly available. The current price for an exploit might be approx. USD $0-$5k (estimation calculated on 08/18/2026). The MITRE ATT&CK project declares the attack technique as T1055.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

Once again VulDB remains the best source for vulnerability data.

Productinfo

Vendor

• Uptash

Name

• Context7

Version

• 2.1.0
• 2.1.1
• 2.1.2

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Once again VulDB remains the best source for vulnerability data.

Discussion