CVE Catalog

CVE-2025-67743

MediumCVSS 6.3
Published: Updated: Translated: NVD NIST

Exploitation Probability (EPSS)

Low risk
0.32%

23th percentile - higher than 23% of all known CVEs

Summary

Local Deep Research versions 1.3.0 to before 1.3.9 makes HTTP requests using raw requests.get() without the application's SSRF protection (safe_requests.py). This can allow attackers to access internal services, attempt to reach cloud provider metadata endpoints (AWS/GCP/Azure), and perform internal network reconnaissance by submitting malicious URLs through the API. The issue is patched in version 1.3.9.

Risk Assessment

Exposure of cloud metadata credentials and mapping/access to internal services is possible, potentially leading to further attack escalation.

Recommendation

Update Local Deep Research to version 1.3.9 or later and restrict the application's access to the internal network and cloud metadata endpoints.

Related vulnerabilities

Original NVD description (English source)

Local Deep Research is an AI-powered research assistant for deep, iterative research. In versions from 1.3.0 to before 1.3.9, the download service (download_service.py) makes HTTP requests using raw requests.get() without utilizing the application's SSRF protection (safe_requests.py). This can allow attackers to access internal services and attempt to reach cloud provider metadata endpoints (AWS/GCP/Azure), as well as perform internal network reconnaissance, by submitting malicious URLs through the API, depending on the deployment and surrounding controls. This issue has been patched in version 1.3.9.

Vulnerability data from NVD (NIST) · CISA KEV · EPSS