Host file overwrite via diff reference argument injection
Published Oct 1, 2026 · Updated Oct 1, 2026
Argument injection in AWS Security Agent MCP Server before 0.2.0 lets context-dependent attackers overwrite host files through a crafted diff reference. The diff scan operation fails to constrain the supplied reference before command-argument interpretation, enabling file creation, overwrite, or truncation outside the workspace. Exploitation requires a crafted reference to reach the local MCP operation, and affected files are limited by the server process's host permissions.
Summary
What happened
Argument injection in AWS Security Agent MCP Server before 0.2.0 lets context-dependent attackers overwrite host files through a crafted diff reference. The diff scan operation fails to constrain the supplied reference before command-argument interpretation, enabling file creation, overwrite, or truncation outside the workspace. Exploitation requires a crafted reference to reach the local MCP operation, and affected files are limited by the server process's host permissions.
The record
- CVE
- CVE-2026-97662
- Published
- Oct 1, 2026
- Updated
- Oct 1, 2026
- Vendor
- Amazon Web Services
- Product
- AWS Security Agent MCP Server
- Classifications
- T1565.001
- Attack vector
- Unavailable
- Privileges
- Unavailable
Timeline
How it unfolded
- Oct 1, 2026CVE publishedPublication date reported by the CVE source.
- Oct 1, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.1.1 <0.2.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Activity data is delayed. The latest report is Sep 28, 2026.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started