CVE-2026-75130 Uptash CVE debrief

Who should care

Defenders responsible for AI coding agents, particularly those using Context7, should assess their exposure to this vulnerability and implement necessary mitigations. This includes verifying the presence of vulnerable Context7 versions, assessing the risk of credential exfiltration and file deletion, and implementing compensating controls to mitigate potential impacts. Security teams should also monitor for suspicious activity related to environment files.

Why it matters

CVE-2026-75130 is a medium-severity vulnerability in Context7 that allows attackers to execute malicious instructions in connected AI coding agents. Defenders should prioritize verifying the presence of this vulnerability, assessing exposure, and implementing mitigations to prevent potential impacts.

• Verify the presence of vulnerable Context7 versions in your environment
• Assess the risk of credential exfiltration and file deletion
• Implement compensating controls to mitigate potential impacts
• Monitor for suspicious activity related to environment files and file deletion

Technical summary

The vulnerability is caused by a lack of sanitization in the Custom AI Instructions feature of Context7, allowing attackers to inject malicious instructions. This can lead to exfiltration of credentials from environment files and destructive file deletion on the victim's machine. The vulnerability affects Context7 through version 2.1.2 and can be triggered through the Custom AI Instructions feature served via the MCP server. Defenders should prioritize verifying the presence of this vulnerability in their AI coding agents and assess exposure to Custom AI Instructions.

Defensive priority

Defenders should prioritize verifying the presence of this vulnerability in their AI coding agents and assess exposure to Custom AI Instructions. Inventory checks and compensating controls should be implemented to mitigate potential impacts.

Recommended defensive actions

• Verify the presence of Context7 version 2.1.2 or earlier in your environment
• Assess exposure to Custom AI Instructions in your AI coding agents
• Implement compensating controls to mitigate potential impacts
• Monitor for suspicious activity related to environment files and file deletion
• Review vendor guidance for patching or mitigating the vulnerability
• Conduct an inventory of AI coding agents using Context7 to identify potential exposure
• Track changes to environment files and monitor for unauthorized access

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, but its actual impact and affected versions require verification from official sources. The vendor and product names are not specified, adding to the uncertainty.

Sources and references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.