CVE-2026-102697

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.

Critical authentication bypass vulnerability in Ollama platform's API endpoints up to v0.12.3. Multiple API endpoints are exposed without authentication, allowing remote attackers to perform unauthorized model management operations.

A vulnerability was found in Ollama up to 0.31.1. This issue affects the function readGGUFV1String of the file fs/ggml/gguf.go of the component GGUF Decoder. Performing a manipulation results in integer overflow. The attack is possible to be carried out remotely. The exploit has been made public and could be used. Upgrading to version 0.31.2-rc1 is capable of addressing this issue.

Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to redirect blob downloads to arbitrary hosts. An attacker can control a registry, serve a malicious tensor-layer manifest, and cause the server to issue GET requests to internal hosts including cloud metadata endpoints.

Ollama (HEAD f0078ae) has an uncontrolled memory allocation vulnerability in the GGUF metadata parser. A remote attacker can upload a crafted sub-1KB GGUF file via the blob upload and model create/pull APIs, triggering an unrecoverable Go runtime out-of-memory fatal error or makeslice panic that bypasses recovery middleware and crashes the entire server.

A vulnerability in the downloadBlob function in Ollama allows a remote attacker to cause a denial-of-service (DoS) condition without authentication. The issue stems from improper validation of user-supplied data, leading to an out-of-bounds memory access.

An unauthenticated remote attacker can read and exfiltrate the heap memory of the Ollama server through the model quantization engine, leading to sensitive data exposure.

Ollama up to version 0.18.1 contains a Server-Side Request Forgery (SSRF) vulnerability in the Model Pull API component (file server/download.go). An attacker can remotely manipulate the request, leading to requests being sent to internal resources.

Ollama versions 0.11.5-rc0 through 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid media before passing it to the mtmd_helper_bitmap_init_from_buf function. This function can return NULL for malformed input, but the code does not check this return value before dereferencing the pointer in subsequent operations.