Secure Autonomous
FeedbackGet alertsCheck a deployment
Signals › SIG-2026-11-10-001

CVE-2026-123809: Dynatrace Model Context Protocol (MCP) Server before 2.0.0 lets values in a workflow-creation tool call carry template expressions that the workflow engine later evaluates

The National Vulnerability Database record says that before version 2.0.0 the Dynatrace Model Context Protocol (MCP) Server's create_workflow_for_notification tool inserted caller-controlled values into a persistent Dynatrace workflow without neutralizing Jinja2 expressions, so that with a valid Slack connector the workflow can disclose event or tenant metadata to an attacker-selected channel, and that exploitation requires either an MCP prompt-injection path or an operator approving a prompt that displays the template fragment literally.

VulnerabilitySoftware agents · Enterprise work agentsRecord published 2026-11-09Posted 2026-11-10
SIG-2026-11-10-001National Vulnerability Database record ↗

The record

Kind
Vulnerability
Source record
CVE-2026-123809 (National Vulnerability Database): Dynatrace MCP Server prior to 2.0.0, create_workflow_for_notification template-expression injection; published 9 November 2026 (National Vulnerability Database record)
Record published
2026-11-09
Posted here
2026-11-10
World
Software agents · Enterprise work agents
Controls concerned
Retrieved content as data C-I1
Checked
Checked against its record on 2026-11-10 by a reader who did not draft it; report verification/reports/SIG-2026-11-10-001-2026-11-10.md.

A signal's controls are the ones its record points at, the exposure; a case's controls are the ones its records show were absent or failed, so the two can differ.

What a signal is. A signal records what a primary record says; it assigns no fault. It is lighter than a case: one dated item from one record, tagged with the world, sector and controls it touches. It becomes a case when it meets the bar for one.

New signals like this, once a week. A short email when a case, signal or rule touches software agents. Free; unsubscribe in one click.

Get the weekly email

Newer: OpenAI misalignment report: agents in two cybersecurity evaluation runs reused peers' credentials and scripts to run root commands in continuous integration (CI) workloads on OpenAI research clusters, 19 July 2026
Older: Malbear Labs report: an exposed workspace shows a jailbroken DeepSeek agent harness running more than two weeks of largely unsupervised intrusion activity against a European telecommunications provider and organizations hosted on its infrastructure (November 2026)

Is this wrong? Dispute it with the record that shows otherwise. All signals · RSS feed.

Help shape the Register

A person reads every answer; changes it leads to are logged in the methodology. To dispute a claim or reply for a named company, use Respond, dispute, or submit.

Did this page help with what you came to do?