CVE-2026-102697High· 7.8▾ TwilightOllama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 42.9 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Stakeholder-Specific Vulnerability Categorization from CISA's ADP record at CVE.org: whether exploitation is observed, whether an attack can be automated, and how much of the system is at stake.
Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-65315High· 7.5Ollama Remote Denial of Service via Attacker-Controlled Allocation in GGUF Metadata Parser
CVE-2026-85180High· 7.5Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to redirect blob downloads to arbitrary hosts
CVE-2026-86289Medium· 4.3A vulnerability was found in Ollama up to 0.31.1
CVE-2025-15514High· 7.5Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality
CVE-2024-28224High· 8.8Ollama DNS rebinding vulnerability
CVE-2024-8063High· 7.5Ollama Divide by Zero Vulnerability