CVE-2025-61784
CVE-2025-61784 is a high-severity vulnerability in Hiyouga Llama-factory with a CVSS 3.x base score of 7.6. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-918.
Key facts
- Severity: High (CVSS 3.x base score 7.6)
- EPSS exploit prediction: 0% (27th percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2025-31881
- Weakness: CWE-918
- Affected product: Hiyouga Llama-factory
- Published:
- Last modified:
Description
LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server's filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.
Frequently asked questions
- What is CVE-2025-61784?
- LLaMA-Factory is a tuning library for large language models. Prior to version 0.9.4, a Server-Side Request Forgery (SSRF) vulnerability in the chat API allows any authenticated user to force the server to make arbitrary HTTP requests to internal and external networks. This can lead to the exposure of sensitive internal services, reconnaissance of the internal network, or interaction with third-party services. The same mechanism also allows for a Local File Inclusion (LFI) vulnerability, enabling users to read arbitrary files from the server's filesystem. The vulnerability exists in the `_process_request` function within `src/llamafactory/api/chat.py.` This function is responsible for processing incoming multimodal content, including images, videos, and audio provided via URLs. The function checks if the provided URL is a base64 data URI or a local file path (`os.path.isfile`). If neither is true, it falls back to treating the URL as a web URI and makes a direct HTTP GET request using `requests.get(url, stream=True).raw` without any validation or sanitization of the URL. Version 0.9.4 fixes the underlying issue.
- How severe is CVE-2025-61784?
- CVE-2025-61784 has a CVSS 3.x base score of 7.6, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity low, and availability low.
- Is CVE-2025-61784 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (27th percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2025-61784?
- CVE-2025-61784 affects Hiyouga Llama-factory. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2025-61784?
- Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
- Does CVE-2025-61784 have an EU (EUVD) identifier?
- Yes. CVE-2025-61784 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-31881.
- When was CVE-2025-61784 published?
- CVE-2025-61784 was published on 2025-10-07 and last updated on 2026-06-17.
References
- https://github.com/hiyouga/LLaMA-Factory/commit/95b7188090a1018935c9dc072bfc97f24f1c96e9
- https://github.com/hiyouga/LLaMA-Factory/security/advisories/GHSA-527m-2xhr-j27g
Affected products (1)
- cpe:2.3:a:hiyouga:llama-factory:*:*:*:*:*:*:*:*
More vulnerabilities in Hiyouga Llama-factory
- CVE-2026-58116 — Critical (CVSS 9.8): LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to…
- CVE-2025-53002 — High (CVSS 8.3): LLaMA-Factory is a tuning library for large language models. A remote code execution vulnerability was discovered in…
- CVE-2024-52803 — High (CVSS 7.5): LLama Factory enables fine-tuning of large language models. A critical remote OS command injection vulnerability has…
- CVE-2025-46567 — Medium (CVSS 6.1): LLama Factory enables fine-tuning of large language models. Prior to version 1.0.0, a critical vulnerability exists in…
All CVEs affecting Hiyouga Llama-factory →
Other CWE-918 (Server-Side Request Forgery (SSRF)) vulnerabilities
- CVE-2026-47938 — Critical (CVSS 10.0): Adobe Campaign Classic (ACC) versions 7.4.3 build 9394 and earlier are affected by a Server-Side Request Forgery (SSRF)…
- CVE-2026-35431 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Microsoft Entra ID Entitlement Management allows an unauthorized attacker to…
- CVE-2026-32186 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Microsoft Bing allows an unauthorized attacker to elevate privileges over a…
- CVE-2026-33107 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Azure Databricks allows an unauthorized attacker to elevate privileges over a…
- CVE-2026-32871 — Critical (CVSS 10.0): FastMCP is a Pythonic way to build MCP servers and clients. Prior to version 3.2.0, the OpenAPIProvider in FastMCP…
- CVE-2026-32169 — Critical (CVSS 10.0): Server-side request forgery (ssrf) in Azure Cloud Shell allows an unauthorized attacker to elevate privileges over a…
Browse all CWE-918 (Server-Side Request Forgery (SSRF)) vulnerabilities →