- CVSS
- HIGH · 7.8v3.1CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-09-29
- Weakness
- CWE-863
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-102697
Description
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.
References
- https://github.com/ollama/ollama
- https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L204-L206
- https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L389
- https://github.com/ollama/ollama/commit/a2b3a5e9a3956bc0700a8505580c11faf4da09b5
- https://github.com/ollama/ollama/releases/tag/v0.31.2
- https://www.vulncheck.com/advisories/ollama-0.14.0-before-0.31.2-experimental-agent-bash-approval-bypass-via-prefix-based-authorization
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-102697 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.