Dynatrace MCP Server: Workflow template injection via create_workflow_for_notification
- Exploited
- No known exploitation
- Fix
- Fixed in 2.0.0
- Who is exposed
- Not reported
Do first: Upgrade to a fixed version: 2.0.0.
- Published
- Last modified
- A 0-100 score for how much a CVE matters across the industry: exploitation, exposure, how widely the software is used, severity and whether a fix exists.What do these mean? →
- 11/100 · provisional
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
Summary
Dynatrace MCP Server's create_workflow_for_notification tool fails to neutralize template expressions in its teamName, problemType, and channel values, so an attacker can reach it remotely without logging in, but only if a user takes an action such as approving a prompt that displays the injected text. If the created workflow has a valid Slack connector, the attacker could disclose event or tenant metadata to a Slack channel of their choosing, and the malicious workflow remains in the tenant after the session ends.
Written by anthropic/claude-haiku-5.5 from the sources below. Verify against them.
Read the original description
Dynatrace MCP Server is an MCP server for Dynatrace Observability. Prior to 2.0.0, the create_workflow_for_notification tool inserts the caller-controlled teamName, problemType, and channel values into a Dynatrace workflow without neutralizing Jinja2 expressions. A caller can place template expressions such as event() in those values, and the workflow engine evaluates them when the persistent workflow runs. When the workflow has a valid Slack connector, the resulting Slack action can disclose event or tenant metadata to an attacker-selected channel; the shipped placeholder connection does not deliver messages by itself. The workflow remains in the tenant after the MCP session and credentials are gone. The isPrivate option defaults to false, making the created workflow tenant-visible unless the caller changes it. Exploitation requires either an MCP prompt-injection path or an operator approving a prompt that displays the template fragment literally. This issue is fixed in version 2.0.0.
cve.now Index
- Exploitation?/40Unknown. No CISA SSVC exploitation rating yet
- Exposure7/25Reachable over the network without a login · Unknown: No advisory context yet
- Reach?/20Unknown. No tracked technology or package matched
- Severity4.2/10CVSS 4.2
- No patch0/5No signal
What would change the score
- Would score about 66 if added to CISA KEV
- Would score about 61 if CISA's SSVC rates exploitation active
- Would score about 26 if advisories confirm default setups are exposed
What to do
Upgrade to a fixed version: 2.0.0.
Timeline
- CVE published
- First seen by cve.now
Affected versions
- dynatrace-oss dynatrace-mcp
fixed in 2.0.0
Evidence 3
- Advisory
- Repository
- Repository
Corrections
None so far.
Something wrong on this page? Report an error. Every fix is listed here.
Questions about CVE-2026-123809
Is CVE-2026-123809 being exploited?
It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.Source: cve.now feed data
Which versions are affected by CVE-2026-123809?
dynatrace-mcp: before 2.0.0.Source: cve.now feed data
How do I fix CVE-2026-123809?
Upgrade to a fixed version: 2.0.0.Source: cve.now feed data