VulnerabilityPublished 20 Mar 2026

CVE-2026-33010: doobidoo mcp-memory-service · Permissive Cross-domain Policy with Untrusted Domains

Affects doobidoo mcp-memory-serviceSource CVE Database V5

Compare

Not known to be exploited · CVSS 8.1 High : upgrade to 10.25.1 soon.

Data as of 1 Nov 2026, 22:58 UTC

CVSS 3.1 base score

8.1High

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 33% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 10.25.1

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: Required
Scope: Unchanged
Confidentiality: High
Integrity: High
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: Required: Successful exploitation of this vulnerability requires a user to take some action before the vulnerability can be exploited.
Scope: Unchanged: An exploited vulnerability can only affect resources managed by the same security authority. In this case, the vulnerable component and the impacted component are either the same, or both are managed by the same security authority.
Confidentiality: High: There is total loss of confidentiality, resulting in all resources within the impacted component being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact.
Integrity: High: There is a total loss of integrity, or a complete loss of protection. For example, the attacker is able to modify any/all files protected by the impacted component. Alternatively, only some files can be modified, but malicious modification would present a direct, serious consequence to the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 20 Mar 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 1 Nov 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade mcp-memory-service and doobidoo/mcp-memory-service to 10.25.1.

Affected software

Product	Affected	Fixed in
doobidoomcp-memory-service	Affected <10.25.1	Fixed in 10.25.1
GitHubdoobidoo/mcp-memory-service`pkg:github/doobidoo/mcp-memory-service`Other threats	Affected <10.25.1	Fixed in 10.25.1

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

To mitigate CVE-2026-33010, organizations should immediately upgrade mcp-memory-service to version 10.25.1 or later, where the vulnerability is patched. If upgrading is not immediately feasible, administrators should disable the HTTP server by setting MCP_HTTP_ENABLED=false to prevent exposure of the vulnerable API. Additionally, disable anonymous access by setting MCP_ALLOW_ANONYMOUS_ACCESS=false to enforce authentication and prevent unauthorized API usage. Review and tighten CORS policies to avoid using wildcard '*' for allow_origins and disallow credentials when origins are not explicitly trusted. Implement strict origin whitelisting to restrict cross-origin requests only to trusted domains. Monitor network traffic and logs for unusual cross-origin requests or unauthorized API access attempts. Employ web application firewalls (WAFs) to detect and block suspicious cross-origin requests targeting the service. Educate developers and administrators about secure CORS configurations and the risks of permissive cross-domain policies. Finally, conduct regular security assessments and penetration tests to verify that no other misconfigurations expose the service to similar risks.

Description

mcp-memory-service is an open-source memory backend for multi-agent systems. Prior to version 10.25.1, when the HTTP server is enabled (MCP_HTTP_ENABLED=true), the application configures FastAPI's CORSMiddleware with allow_origins=['*'], allow_credentials=True, allow_methods=["*"], and allow_headers=["*"]. The wildcard Access-Control-Allow-Origin: * header permits any website to read API responses cross-origin. When combined with anonymous access (MCP_ALLOW_ANONYMOUS_ACCESS=true) - the simplest way to get the HTTP dashboard working without OAuth - no credentials are needed, so any malicious website can silently read, modify, and delete all stored memories. This issue has been patched in version 10.25.1.

Impact

The impact of CVE-2026-33010 is substantial for organizations using the affected versions of mcp-memory-service with HTTP enabled and anonymous access allowed. Attackers can exploit this vulnerability to bypass same-origin policy restrictions and gain unauthorized access to sensitive memory data stored by the service. This can lead to complete compromise of data confidentiality and integrity, as attackers can read, modify, or delete stored memories. Such unauthorized access could disrupt multi-agent system operations, corrupt data, or leak sensitive information to external entities. The vulnerability does not affect availability directly but can cause operational disruptions through data manipulation. Given the ease of exploitation—no authentication or special privileges required—and the broad scope of affected systems, organizations face a high risk of data breaches and system misuse. This threat is especially critical for deployments exposed to the internet or untrusted networks where malicious websites can lure users to trigger cross-origin requests. The lack of known exploits in the wild suggests the vulnerability is newly disclosed, but the high CVSS score and straightforward exploitation path necessitate immediate remediation to prevent potential attacks.

CWE-942Permissive Cross-domain Security Policy with Untrusted Domains (opens in a new tab)
Variant weaknessOWASP Top 10 A02:2025: Security Misconfiguration (opens in a new tab)
The product uses a web-client protection mechanism such as a Content Security Policy (CSP) or cross-domain policy file, but the policy includes untrusted domains with which the web client is allowed to communicate.
Architecture and Design · Operation · Attack Surface Reduction
Define a restrictive Content Security Policy or cross-domain policy file.
Architecture and Design · Operation · Attack Surface Reduction
Avoid using wildcards in the CSP / cross-domain policy file. Any domain matching the wildcard expression will be implicitly trusted, and can perform two-way interaction with the target server.
Architecture and Design · Operation · Environment Hardening
For Flash, modify crossdomain.xml to use meta-policy options such as 'master-only' or 'none' to reduce the possibility of an attacker planting extraneous cross-domain policy files on a server.
OWASP ASVS 4.0.3
V8.3.8 (opens in a new tab)
V1.14.1 (opens in a new tab)
V13.4.2 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

github.com/doobidoo/mcp-memory-service/security/advisories/GHSA-g9rg-8vq5-mpwm (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 27 Mar 2026, 19:31 UTC

WeaknessesCWE-942

Technical details

References

Community reviews

Related threats