Vendor
Universal Tool Calling Protocol vulnerabilities
Updated . Rebuilt every hour.
Junglewise Threat Intelligence has tracked 8 vulnerabilities in Universal Tool Calling Protocol: 0 in the last 7 days and 4 in the last 90 days, 1 of them critical and 0 exploited in the wild. The most recent, CVE-2026-101061, was published on 27 September 2026. Nothing in the last four weeks, down from 4 vulnerabilities in the four before. 3 technologies have a page of their own.
- Last 7 days
- 0
- Last 90 days
- 4
- Critical, all time
- 1
- Exploited in the wild
- 0
About Universal Tool Calling Protocol
Universal Tool Calling Protocol is an open standard for communication between AI agents and external tools.
Universal Tool Calling Protocol technologies
Latest Universal Tool Calling Protocol vulnerabilities
- CVE-2026-101061: utcp-gql and utcp-websocket server-side request forgery via URL validation bypassmediumCVSS 4.7
- CVE-2026-101060: python-utcp server-side request forgery via unvalidated HTTP redirectshighCVSS 8.2
- CVE-2026-101059: utcp-http OAuth2 tokenUrl validation bypass in OpenAPI conversionhighCVSS 7.1
- CVE-2026-101058: python-utcp server-side request forgery via remote HTTP manualmediumCVSS 6.9
- python-utcp localhost prefix validation bypass in utcp-gql and utcp-websocketmediumCVSS 6.3
- CVE-2026-12210: Universal Tool Calling Protocol SSRF via localhost validation bypassmediumCVSS 6.3EPSS 0.2%
- CVE-2026-45366: typescript-utcp SSRF in @utcp/http via OpenAPI spec redirectionmediumCVSS 4.7EPSS 0.2%
- CVE-2026-45369: python-utcp OS command injection in CLI communication protocolcriticalCVSS 10EPSS 0.4%
Most severe Universal Tool Calling Protocol vulnerabilities
Exploited in the wild first, then by severity and CVSS score.
- CVE-2026-45369: python-utcp OS command injection in CLI communication protocolcriticalCVSS 10EPSS 0.4%
- CVE-2026-101060: python-utcp server-side request forgery via unvalidated HTTP redirectshighCVSS 8.2
- CVE-2026-101059: utcp-http OAuth2 tokenUrl validation bypass in OpenAPI conversionhighCVSS 7.1
- CVE-2026-101058: python-utcp server-side request forgery via remote HTTP manualmediumCVSS 6.9
- CVE-2026-12210: Universal Tool Calling Protocol SSRF via localhost validation bypassmediumCVSS 6.3EPSS 0.2%
- python-utcp localhost prefix validation bypass in utcp-gql and utcp-websocketmediumCVSS 6.3
- CVE-2026-45366: typescript-utcp SSRF in @utcp/http via OpenAPI spec redirectionmediumCVSS 4.7EPSS 0.2%
- CVE-2026-101061: utcp-gql and utcp-websocket server-side request forgery via URL validation bypassmediumCVSS 4.7
Vulnerabilities per week
Nothing in the last four weeks, down from 4 vulnerabilities in the four before. The last 13 weeks, by the week each vulnerability was published.
| Week of | Bar | Vulns | Critical |
|---|---|---|---|
| 17 Aug 2026 | 0 | 0 | |
| 24 Aug 2026 | 0 | 0 | |
| 31 Aug 2026 | 0 | 0 | |
| 7 Sep 2026 | 0 | 0 | |
| 14 Sep 2026 | 0 | 0 | |
| 21 Sep 2026 | 4 | 0 | |
| 28 Sep 2026 | 0 | 0 | |
| 5 Oct 2026 | 0 | 0 | |
| 12 Oct 2026 | 0 | 0 | |
| 19 Oct 2026 | 0 | 0 | |
| 26 Oct 2026 | 0 | 0 | |
| 2 Nov 2026 | 0 | 0 | |
| 9 Nov 2026 | 0 | 0 |
Embed a badge
A live badge for a README, a status page or an internal wiki: how many Universal Tool Calling Protocol vulnerabilities were published in the last 7 days and how many of them are critical, refreshed hourly.
[](https://junglewise.ai/threats/vendors/universal-tool-calling-protocol)<a href="https://junglewise.ai/threats/vendors/universal-tool-calling-protocol"><img src="https://junglewise.ai/threats/vendors/universal-tool-calling-protocol/badge.svg" alt="Universal Tool Calling Protocol vulnerabilities" /></a>How this is built
Junglewise Threat Intelligence collects vulnerabilities from NVD, GitHub Security Advisories, OSV, the CISA Known Exploited Vulnerabilities catalog, FIRST EPSS and vendor advisories, and matches each one to the technologies and vendors it affects. Dates are the date a vulnerability was published, in UTC.
The pages are rebuilt from the database every hour. Frozen weekly and monthly reports never change once published, so they can be cited.
Use this data
The same data is at https://junglewise.ai/threats/vendors/universal-tool-calling-protocol.json, and this page as text at https://junglewise.ai/threats/vendors/universal-tool-calling-protocol.md, for scripts and language models. It is free to reuse under CC BY 4.0 with a link back to this page.
Cite as: Junglewise Threat Intelligence, "Universal Tool Calling Protocol vulnerabilities", https://junglewise.ai/threats/vendors/universal-tool-calling-protocol, 9 November 2026.