CVE-2026-110202

Affects: prompt injection

CVSS
HIGH · 8.8v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Published
2026-10-13
Weakness
CWE-436
Source
nvd.nist.gov/vuln/detail/CVE-2026-110202

Description

Roo Code through 3.54.0 contains a command approval bypass vulnerability in getCommandDecision() that allows attackers to auto-approve denied shell commands by prefixing them with a bare >& redirect. Attackers using indirect prompt injection can make the allowlist match a redirect target like echo while the shell runs the denied command on the developer machine.

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-2026-110202 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