What is the CVSS score of CVE-2026-27961?

CVE-2026-27961 has a CVSS 3.1 base score of 8.8 (High). CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H. EPSS exploitation probability: 0.1%.

Which versions of AI / ML are affected by CVE-2026-27961?

A critical Server-Side Template Injection vulnerability in Agenta's API server (CVE-2026-27961, CVSS 8.8) allows attackers to execute arbitrary code on affected systems.. A patch is available.

How to fix or mitigate CVE-2026-27961?

Within 24 hours: Isolate affected Agenta instances from production networks and disable template evaluation features if operationally feasible. Within 7 days: Implement network segmentation, deploy WAF rules to block template injection payloads, and conduct urgent security assessment of logs for exploitation attempts. Within 30 days: Upgrade to Agenta 0.86.8 or later when patch is released, or evaluate alternative LLMOps platforms if upgrading is not viable.

AI / ML CVE-2026-27961

HIGH

Improper Neutralization of Special Elements Used in a Template Engine (CWE-1336)

2026-02-26 security-advisories@github.com

Code Injection AI / ML Agenta

8.8

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

8.8 HIGH

AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Attack Vector

Network

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Lifecycle Timeline

Analysis Generated

Mar 12, 2026 - 21:55 vuln.today

CVE Published

Feb 26, 2026 - 02:16 nvd

HIGH 8.8

DescriptionGitHub Advisory

Agenta is an open-source LLMOps platform. A Server-Side Template Injection (SSTI) vulnerability exists in versions prior to 0.86.8 in Agenta's API server evaluator template rendering. Although the vulnerable code lives in the SDK package, it is executed server-side within the API process when running evaluators. This does not affect standalone SDK usage - it only impacts self-hosted or managed Agenta platform deployments. Version 0.86.8 contains a fix for the issue.

AnalysisAI

Authenticated attackers can execute arbitrary code on Agenta API servers through server-side template injection in the evaluator template rendering functionality, affecting self-hosted and managed platform deployments prior to version 0.86.8. The vulnerability requires valid credentials but allows complete compromise of the affected server with high confidentiality, integrity, and availability impact. Organizations running Agenta should upgrade to version 0.86.8 or later immediately.

Technical ContextAI

Affects Agenta. Agenta is an open-source LLMOps platform. A Server-Side Template Injection (SSTI) vulnerability exists in versions prior to 0.86.8 in Agenta's API server evaluator template rendering. Although the vulnerable code lives in the SDK package, it is executed server-side within the API process when running evaluators. This does not affect standalone SDK usage — it only impacts self-hosted or managed Agenta platform deployments. Version 0.86.8 contains a fix for the issue.