CVE-2026-37006 gpt-researcher CVE debrief

Who should care

Defenders responsible for gpt-researcher deployments should assess exposure and apply patches or mitigations. Security teams and administrators of affected systems should prioritize verification and remediation.

Why it matters

Defenders should prioritize assessing exposure and applying patches or mitigations for gpt-researcher deployments due to the critical severity and potential for code execution.

• Potential code execution by unauthenticated remote attackers
• Critical severity with CVSS score of 9.8
• Possible exploitation via malicious Model Context Protocol configurations

Technical summary

The vulnerability exists in the WebSocket endpoint of gpt-researcher v0.14.7 and earlier versions. An unauthenticated remote attacker can exploit this via malicious Model Context Protocol configurations to achieve code execution. The CVSS score is 9.8, indicating critical severity.

Defensive priority

Immediate attention is required to assess exposure and apply patches or mitigations.

Recommended defensive actions

• Assess exposure of gpt-researcher deployments to this vulnerability
• Apply patches or mitigations to vulnerable gpt-researcher instances
• Verify Model Context Protocol configurations for potential malicious activity

Evidence notes

The CVE record and NVD entry provide details on the vulnerability, including its critical severity and potential for code execution. The evidence is based on the official CVE Program record and NIST NVD detail page. The affected scope is gpt-researcher v0.14.7 and earlier versions. Defenders should verify the Model Context Protocol configurations and assess exposure. The known affected scope is limited to gpt-researcher deployments. The unknown affected scope may include other products

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.