Browse / AI Framework and Platform Flaws / CVE-2025-51471
Ollama vulnerable to Cross-Domain Token Exposure
- Class
- AI Framework and Platform Flaws (filed by a model that read the advisory)
- Technique
- Information exposure
- Affected
- github.com/ollama/ollama (Go)
- CVSS
- CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:L/A:N
- EPSS
- 18.5% chance of exploitation in 30 days
How it works, in short
A malicious WWW-Authenticate realm makes the client send its stored bearer token to an attacker-chosen host during a registry pull. (Our summary, written by a model. The source text is below.)
Details
Cross-Domain Token Exposure in server.auth.getAuthorizationToken in Ollama 0.6.7 allows remote attackers to steal authentication tokens and bypass access controls via a malicious realm value in a WWW-Authenticate header returned by the /api/pull endpoint.
References
- https://nvd.nist.gov/vuln/detail/CVE-2025-51471
- https://github.com/ollama/ollama/pull/10750
- https://github.com/ollama/ollama
- https://github.com/pypa/advisory-database/tree/main/vulns/ollama/PYSEC-2025-147.yaml
- https://huntr.com/bounties/94eea285-fd65-4e01-a035-f533575ebdc2
- https://www.gecko.security/blog/cve-2025-51471
Source: GitHub Advisory Database, used under CC BY 4.0.