# CVE-2024-6587: SSRF in berriai/litellm - Exploited (CISA KEV): no - Published: 2024-09-13 - CVSS: 7.5 HIGH (v3.0) - EPSS: 34.4% (98th percentile) - CWE: CWE-918 A Server-Side Request Forgery (SSRF) vulnerability exists in berriai/litellm version 1.38.10. This vulnerability allows users to specify the `api_base` parameter when making requests to `POST /chat/completions`, causing the application to send the request to the domain specified by `api_base`. This request includes the OpenAI API key. A malicious user can set the `api_base` to their own domain and intercept the OpenAI API key, leading to unauthorized access and potential misuse of the API key. ## Edge WAF coverage (claimed by vendors, not measured) | Vendor | Status | First rule | Days after publication | |---|---|---|---| | Cloudflare | Rule off by default | 2025-07-21 | 311 | | AWS | No public claim | — | — | | Microsoft Azure | No public claim | — | — | | Google Cloud | No public claim | — | — | | Fastly | Before feed history | — | — | | F5 | No public claim | — | — | | Akamai | No public source | — | — | | OWASP CRS | No public claim | — | — | ### Cloudflare - 2025-07-21 · new · rule 6ab3bd3b58fb4325ac2d3cc73461ec9e · default Log > BerriAI - SSRF - CVE:CVE-2024-6587. Previous action: Log. New action: Log. This is a New Detection Source: https://developers.cloudflare.com/changelog/post/2025-07-21-waf-release/ - 2025-07-28 · new · rule 6ab3bd3b58fb4325ac2d3cc73461ec9e · default Disabled > BerriAI - SSRF - CVE:CVE-2024-6587. Previous action: Log. New action: Disabled. This is a New Detection Source: https://developers.cloudflare.com/changelog/post/2025-07-28-waf-release/ ## Our test (measured) - OWASP Core Rule Set 4.25.0, paranoia level 1, anomaly threshold 5, default CRS settings: passed (0 of 1 requests blocked), template CVE-2024-6587, 2026-11-02 - OWASP Core Rule Set 4.25.0, paranoia level 2, anomaly threshold 5, default CRS settings: blocked (1 of 1 requests blocked), template CVE-2024-6587, 2026-11-02 "No public claim" means no vendor statement names this CVE; "Before feed history" means the CVE is older than the vendor feed. In both cases generic rules may still block it. HTML: https://cve.vigilbase.com/cve/CVE-2024-6587 · JSON: https://cve.vigilbase.com/api/v1/cves/CVE-2024-6587