CVE-2026-87913VulnerabilityPublished 10 Sep 2026

CVE-2026-87913: AWS Security Agent MCP server · Unverified ownership

Affects AWS Security Agent MCP serverSource CVE Database V5

Not known to be exploited · CVSS 5.9 Medium · patch available : update AWS Security Agent MCP server when convenient.

Data as of 25 Oct 2026, 19:02 UTC

CVSS 3.1 base score

5.9Medium

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

EPSS: 0.4% chance of exploitation in 30 days – higher than 38% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available

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

Attack Vector: Network
Attack Complexity: High
Privileges Required: None
User Interaction: Required
Scope: Unchanged
Confidentiality: High
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: High: A successful attack depends on conditions beyond the attacker's control. That is, a successful attack cannot be accomplished at will, but requires the attacker to invest in some measurable amount of effort in preparation or execution against the vulnerable component before a successful attack can be expected. For example, a successful attack may require an attacker to: gather knowledge about the environment in which the vulnerable target/component exists; prepare the target environment to improve exploit reliability; or inject themselves into the logical network path between the target and the resource requested by the victim in order to read and/or modify network communications (e.g., a man in the middle attack).
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: 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 10 Sep 2026
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 2026-10-25.

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 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
AWSAWS Security Agent MCP server	Affected >=0.1.0 <=0.1.5	Fixed in–
PyPIawslabs-security-agent-mcp-server`pkg:pypi/awslabs-security-agent-mcp-server`Other threats	Affected =0.1.0	Fixed in–

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

AI-suggested

An official fix is available in AWS Security Agent MCP server version 0.2.0. Users should upgrade to this version promptly. Additionally, users must verify that the scan output S3 bucket is owned by their own AWS account, as upgrading does not reclaim bucket names that third parties may have already registered. Follow the vendor advisory at https://aws.amazon.com/security/security-bulletins/2026-105-aws/ for detailed remediation guidance.

Description

A missing S3 bucket ownership verification in the AWS Security Agent MCP server before 0.2.0 version might allow remote attackers to obtain the private source archive of a scanned workspace, including credentials and infrastructure state contained in that archive, via a pre-registered storage bucket whose name is derived from a publicly known account identifier. To remediate this issue, users should upgrade to version 0.2.0. Users should also verify that the scan output bucket in their account is owned by their own account, because upgrading does not release a bucket name that a third party has already registered.

Impact

If exploited, remote attackers could obtain private source archives from scanned workspaces, including sensitive credentials and infrastructure state data. This could lead to unauthorized disclosure of confidential information. The vulnerability does not allow integrity or availability impacts but compromises confidentiality.

Summary

This vulnerability (CVE-2026-87913) in AWS Security Agent MCP server prior to version 0.2.0 is due to missing verification of S3 bucket ownership. An attacker can exploit this by using a pre-registered storage bucket whose name is derived from a publicly known AWS account identifier, potentially gaining access to private source archives of scanned workspaces. These archives may contain sensitive information such as credentials and infrastructure state. The vulnerability has a CVSS 3.1 score of 5.9, reflecting medium severity with network attack vector, high complexity, no privileges required, and user interaction needed. AWS has issued an official fix in version 0.2.0 and advises users to verify bucket ownership to prevent unauthorized access.

CWE-283Unverified Ownership (opens in a new tab)
Base weaknessOWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The product does not properly verify that a critical resource is owned by the proper entity.
Architecture and Design · Operation
Very carefully manage the setting, management, and handling of privileges. Explicitly manage trust zones in the software.
Architecture and Design · Separation of Privilege
Consider following the principle of separation of privilege. Require multiple conditions to be met before permitting access to a system resource.
OWASP Cheat Sheets
Docker Security (opens in a new tab)
Third Party Javascript Management (opens in a new tab)
Virtual Patching (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V1.4.4 (opens in a new tab)
V1.4.5 (opens in a new tab)
V1.10.1 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).
CWE-341Predictable from Observable State (opens in a new tab)
Base weakness
A number or object is predictable based on observations that the attacker can make about the state of the system or network, such as time, process ID, etc.
Implementation
Increase the entropy used to seed a PRNG.
Architecture and Design · Requirements · Libraries or Frameworks
Use products or modules that conform to FIPS 140-2 to avoid obvious entropy problems. Consult FIPS 140-2 Annex C ("Approved Random Number Generators").
Implementation
Use a PRNG that periodically re-seeds itself using input from high-quality sources, such as hardware devices with high entropy. However, do not re-seed too frequently, or else the entropy source might block.
OWASP Cheat Sheets
Forgot Password (opens in a new tab)
OWASP ASVS 4.0.3
V2.3.1 (opens in a new tab)
V2.6.2 (opens in a new tab)
V2.7.6 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 10 Sep 2026, 16:37 UTC

WeaknessesCWE-283, CWE-341

Technical details

References

Community reviews

Related threats