CVE-2026-85675 OWL DocumentProcessingToolkit Server-Side Request Forgery via URL Fetching
Attackers can exploit prompt injection to force the server to fetch internal resources via unfiltered URLs, exposing sensitive data.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-85675?
CVE-2026-85675 is a high-severity server-side request forgery vulnerability in camel-ai owl, published on 4 Sep 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official 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.
Weakness: CWE-918
Which versions are affected by CVE-2026-85675?
How do I fix CVE-2026-85675?
No fix has been published for CVE-2026-85675 yet. Limit exposure of the affected software until one is available.
Upgrade, and send outbound requests through an allow-list that blocks internal addresses. More about Server-side request forgery.
Is CVE-2026-85675 being exploited?
There is no known exploitation of CVE-2026-85675 in the wild and no public exploit code.
Sources
Also known as GHSA-9c7r-jxm8-hgg2.