AI AgentHigh
CVE-2026-102697: Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experim…
- Occurred
- Sep 29, 2026
- Published
- Sep 29, 2026
- Source
- NVD CVE
Summary
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.
Tags
- CVE
- CVE-2026-102697
- cvss:HIGH
- agent-fail:authorization
- agent-fail:injection-direct
- agent-cause:framework-bug
Classification
Category confidence: 95%
Severity confidence: 90%
Rationale: Vulnerability in Ollama agent mode allows prompt injection to bypass authorization controls and execute unauthorized shell commands.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8