CVE-2026-108599

Affects: prompt injection

CVSS
MEDIUM · 4.7v3.1
CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N
Published
2026-10-10
Weakness
CWE-59
Source
nvd.nist.gov/vuln/detail/CVE-2026-108599

Description

phi 0.1.1 through 0.28.4 contains an improper link resolution vulnerability that allows malicious repositories to bypass workspace_only_writes by exploiting lexical-only path checks in the permission gate. Attackers can commit symlinks pointing outside the workspace and use prompt injection to make the write tool write attacker-influenced content to external files without approval.

References

How GTK Cyber trains on this

AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-108599 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.

AI Red-Teaming course →·Browse MITRE ATLAS techniques

Related AI/LLM CVEs

AI security training, taught by people who do the work.

Hands-on courses on adversarial AI, prompt injection, and ML pipeline security.

Explore AI Red-Teaming