CVE-2026-85675: Server-Side Request Forgery (SSRF) in camel-ai owl

The camel-ai owl product's DocumentProcessingToolkit contains an SSRF vulnerability in the extract_document_content tool. This tool fetches URLs provided by users without validating or restricting the URL scheme, host, or IP address. As a result, attackers can craft malicious input that causes the server to make unauthorized requests to internal or protected resources. The vulnerability has a CVSS 4.0 base score of 8.7, indicating high severity. No official remediation or patch information is currently available, and no known exploits in the wild have been reported.

Successful exploitation allows an unauthenticated attacker to induce the server to make arbitrary HTTP requests to internal or external systems, potentially exposing sensitive internal resources or data. The responses from these requests are returned to the agent context, which could lead to information disclosure or further attack chaining. The vulnerability does not require privileges or user interaction to exploit.

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should consider restricting or sanitizing inputs to the extract_document_content tool to prevent injection of malicious URLs. Network-level controls to limit outbound HTTP requests from the server to internal resources may also reduce risk.