CVE-2026-76066

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.
Configurations

No configuration.

History

22 Oct 2026, 17:17

Type Values Removed Values Added
References
  • () https://github.com/crestalnetwork/intentkit/commit/5b91da5734d1ac16cd656fa66a86caf8f15cd671 -
Summary (en) IntentKit through 2.6.3 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. (en) 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.

15 Oct 2026, 02:20

Type Values Removed Values Added
New CVE

Information

Published : 2026-10-15 02:20

Updated : 2026-10-22 17:17


NVD link : CVE-2026-76066

Mitre link : CVE-2026-76066

CVE.ORG link : CVE-2026-76066


JSON object : View

Products Affected

No product.

CWE
CWE-862

Missing Authorization