CVE-2026-76066

Affects: prompt injection

CVSS: HIGH · 7.5v3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N
Published: 2026-10-15
Weakness: CWE-862
Source: nvd.nist.gov/vuln/detail/CVE-2026-76066

Description

IntentKit through 2.6.3, fixed in commit 5b91da5, contains an authorization bypass vulnerability where the executor validates tool calls against the full tool registry rather than the per-request narrowed tool advertisement enforced by ToolBindingMiddleware, allowing owner-only state-changing tools such as wallet transfer, posting, memory-write, and call-agent to execute without any human-in-the-loop or approval gate. An unauthenticated or public caller in WEB, API, TWITTER, or TELEGRAM contexts can exploit this by supplying the exact de-advertised tool name and arguments via indirect prompt injection or by replaying checkpoint and history data on a reused thread, achieving unauthorized execution of owner-restricted capabilities.

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-2026-76066 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