VulnerabilityPublished 18 Nov 2025

CVE-2025-63603: mcp-server-data-exploration · Command Injection

Affects mcp-server-data-explorationSource CVE Database V5

Not known to be exploited · CVSS 6.5 Medium.

Data as of 26 Oct 2026, 12:29 UTC

CVSS 3.1 base score

6.5Medium

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

EPSS: 0.8% chance of exploitation in 30 days – higher than 58% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

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

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Unchanged
Confidentiality: Low
Integrity: Low
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: None: The vulnerable system can be exploited without any interaction from any user.
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: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact on 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 18 Nov 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: 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 26 Oct 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.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, 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

Affected software

Product	Affected	Fixed in
PyPIreading-plus-ai/mcp-server-data-exploration`pkg:pypi/reading-plus-ai/mcp-server-data-exploration`Other threats	Affected =0.1.6	Fixed in–

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

AI-suggested

Immediate mitigation should include disabling or restricting access to the run_script tool or any functionality that allows execution of user-supplied scripts until a patch is available.
Implement strict input validation and sandboxing to limit the execution environment, explicitly defining or removing the __builtins__ dictionary in the globals parameter passed to exec() to prevent access to dangerous built-in functions.
Employ application-layer firewalls or web application firewalls (WAFs) to detect and block malicious script submissions targeting this vulnerability.
Monitor logs for unusual script execution attempts or anomalous behavior indicative of exploitation attempts.
Network segmentation should be used to isolate the MCP Data Science Server from critical systems to limit potential lateral movement.
Engage with the software vendor or community to obtain patches or updates addressing this vulnerability as soon as they become available.
Conduct regular security assessments and code reviews of custom scripts or extensions running on the server to identify similar insecure coding practices.
Educate development and operations teams about the risks of using exec() with untrusted input and promote safer alternatives.

Description

A command injection vulnerability exists in the MCP Data Science Server's (reading-plus-ai/mcp-server-data-exploration) 0.1.6 in the safe_eval() function (src/mcp_server_ds/server.py:108). The function uses Python's exec() to execute user-supplied scripts but fails to restrict the __builtins__ dictionary in the globals parameter. When __builtins__ is not explicitly defined, Python automatically provides access to all built-in functions including __import__, exec, eval, and open. This allows an attacker to execute arbitrary Python code with full system privileges, leading to complete system compromise. The vulnerability can be exploited by submitting a malicious script to the run_script tool, requiring no authentication or special privileges.

Impact

For European organizations, exploitation of CVE-2025-63603 could lead to complete system compromise of servers running MCP Data Science Server 0.1.6. Attackers could execute arbitrary code with full system privileges, potentially leading to unauthorized access to sensitive data, manipulation or destruction of data science models and datasets, and disruption of critical data processing workflows. This could result in loss of data integrity and confidentiality, impacting decision-making processes and regulatory compliance, especially under GDPR. The vulnerability's unauthenticated nature increases risk, as attackers do not need valid credentials or user interaction, enabling automated mass exploitation attempts. Compromised systems could also serve as footholds for lateral movement within enterprise networks, escalating the threat to broader IT infrastructure. The absence of known exploits in the wild currently reduces immediate risk, but the vulnerability's characteristics warrant proactive mitigation to prevent future attacks. Organizations in sectors relying heavily on data science and AI, such as finance, healthcare, and manufacturing, are particularly at risk due to the criticality of their data and models.

CWE-77Improper Neutralization of Special Elements used in a Command ('Command Injection') (opens in a new tab)
Class weaknessLikelihood of exploit: HighCWE Top 25 (2025): #23OWASP Top 10 A05:2025: Injection (opens in a new tab)
The product constructs all or part of a command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended command when it is sent to a downstream component.
Architecture and Design
If at all possible, use library calls rather than external processes to recreate the desired functionality.
Implementation
If possible, ensure that all external commands called from the program are statically created.
Implementation · Input Validation
Assume all input is malicious. Use an "accept known good" input validation strategy, i.e., use a list of acceptable inputs that strictly conform to specifications. Reject any input that does not strictly conform to specifications, or transform it into something that does.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
Injection Prevention (opens in a new tab)
SQL Injection Prevention (opens in a new tab)
Injection Prevention in Java (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
Attack patterns
LDAP Injection (opens in a new tab)
Command Delimiters (opens in a new tab)
IMAP/SMTP Command Injection (opens in a new tab)
Manipulating Writeable Terminal Devices (opens in a new tab)
Exploiting Multiple Input Interpretation Layers (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

github.com/reading-plus-ai/mcp-server-data-exploration/issues/12 (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 25 Nov 2025, 16:24 UTC

WeaknessesCWE-77

Technical details

References

Community reviews

Related threats