CVE-2026-85675
Received Received - Intake

Server-Side Request Forgery in OWL DocumentProcessingToolkit

Publication date: 2026-09-04

Last updated on: 2026-09-04

Assigner: VulnCheck

Description
OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extract_document_content tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources, with responses returned to the agent context.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-09-04
Last Modified
2026-09-04
Generated
2026-09-04
AI Q&A
2026-09-04
EPSS Evaluated
N/A
NVD
CVE-2026-85675
EUVD
EUVD-2026-71131

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
camel-ai owl to fba1dd5b3a9e8cc15f16221bb002cca7e3de2d9d (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-918 The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This is a Server-Side Request Forgery (SSRF) vulnerability in OWL's DocumentProcessingToolkit. The extract_document_content tool fetches URLs provided by users without validating the scheme, host, or IP address. Attackers can inject malicious URLs through prompt injection to make the server access internal resources, and the responses are returned to the agent context.

Detection Guidance

To detect this SSRF vulnerability in OWL's DocumentProcessingToolkit, monitor network traffic for outbound requests from the extract_document_content tool to internal or unexpected hosts. Check logs for URLs fetched by the tool without proper validation. Use tools like tcpdump or Wireshark to capture requests to loopback, private, or reserved IP ranges. Inspect agent system prompts for instructions to visit URLs from untrusted sources.

Impact Analysis

An attacker could exploit this to access internal services or cloud metadata endpoints, potentially exfiltrating sensitive data. Since the tool is used in agent systems that follow instructions to visit URLs from web search results, indirect prompt injection attacks are possible.

Compliance Impact

This vulnerability could lead to unauthorized access to sensitive data, violating GDPR's data protection principles and HIPAA's security requirements for protected health information. Unauthorized data exposure may result in compliance breaches and legal penalties.

Mitigation Strategies

Immediately update OWL to a patched version that validates URLs in extract_document_content. Implement strict allowlisting for http/https schemes and block requests to loopback, private, link-local, unique-local, reserved IPs, and cloud metadata endpoints. Disable redirects or re-validate them. Treat all tool-supplied URLs as untrusted regardless of source.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-85675. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart