CVE-2026-35651

Affects: prompt injection

CVSS: MEDIUM · 4.3 v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:L/A:N
Published: 2026-04-10
Weakness: CWE-150
Source: nvd.nist.gov/vuln/detail/CVE-2026-35651

Description

OpenClaw versions 2026.2.13 through 2026.3.24 contain an ANSI escape sequence injection vulnerability in approval prompts that allows attackers to spoof terminal output. Untrusted tool metadata can carry ANSI control sequences into approval prompts and permission logs, enabling attackers to manipulate displayed information through malicious tool titles.

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-2026-35651 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