Ollama is vulnerable to path traversal in the /api/pull endpoint due to insufficient validation of layer digests by the digestToPath…
CVE-2026-103663
Ollama is vulnerable to path traversal in the /api/pull endpoint due to insufficient validation of layer digests by the digestToPath function. An unauthenticated remote attacker can specify a path traversal sequence as a layer digest, causing a malicious binary to be written outside the model store. Critically if the server process has write access to /usr/lib/ollama (the default in most Ollama Docker images), an attacker can write the malicious file to that directory. On the next server restart, the file is loaded and executed, resulting in remote code execution as root. This issue was fixed in version 0.35.0.
Proof-of-concept code is published
Public PoC
- Public PoCstriga-ai/CVE-2026-103663
Signals come from Exploit-DB, Metasploit, Nuclei and published proof-of-concept repositories. Their absence means nothing was found, not that nothing exists.
Part of the AI stack
This affects Ollama, in Inference & serving.
Assessment
- CVSS
- 9.4 (v4.0)
- Severity
- Critical
- EPSS
- 0.71% chance of exploitation in the next 30 days
- Known exploited
- Not listed in CISA KEV
- Exploit availability
- Public PoC
- Published
- 8 October 2026
- Last updated
- 17 November 2026
- Assigner
- CERT-PL
CVSS vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
At the source
References
Community proofs of concept
No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.
Submit a proof of concept
Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.
Query this programmatically
Agents can read this through the MCP endpoint, or over HTTP:
curl https://cve.zerocrew.in/api/cve/CVE-2026-103663