CVE-2026-97662 - Argument injection in AWS security-agent-mcp-server diff scan
CVE-2026-97662 is an argument injection vulnerability in the AWS security-agent-mcp-server's diff scan operation. This flaw allows a crafted reference value to be interpreted as a command-line option rather than a revision, enabling an attacker with certain context-dependent capabilities to create, overwrite, or truncate arbitrary files outside the intended workspace directory. The vulnerability affects versions from 0.1.1 up to but not including 0.2.0 of the security-agent-mcp-server.
AI Analysis
Technical Summary
The security-agent-mcp-server, an open-source Model Context Protocol server used by AI assistants for local security scans, contains an argument injection vulnerability in its diff scan feature. Specifically, a crafted reference value supplied to the scan is misinterpreted as a command-line option, which bypasses the server's workspace confinement controls. This allows a context-dependent actor to manipulate files arbitrarily on the host system outside the designated workspace directory. The affected versions are >=0.1.1 and <0.2.0.
Potential Impact
An attacker who can supply a crafted reference value to the diff scan operation can create, overwrite, or truncate arbitrary files on the host system outside the intended workspace directory. This bypasses the server's confinement controls and could lead to unauthorized file manipulation, potentially impacting system integrity or availability depending on the files affected.
Mitigation Recommendations
No explicit patch or remediation details are provided in the bulletin. Patch status is not yet confirmed — check the AWS Security Bulletin for the most current remediation guidance. Until a fix is available, avoid using affected versions or restrict access to the diff scan functionality to trusted users only.
CVE-2026-97662 - Argument injection in AWS security-agent-mcp-server diff scan
Description
CVE-2026-97662 is an argument injection vulnerability in the AWS security-agent-mcp-server's diff scan operation. This flaw allows a crafted reference value to be interpreted as a command-line option rather than a revision, enabling an attacker with certain context-dependent capabilities to create, overwrite, or truncate arbitrary files outside the intended workspace directory. The vulnerability affects versions from 0.1.1 up to but not including 0.2.0 of the security-agent-mcp-server.
Affected software
pkg:github/aws/security-agent-mcp-serverRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The security-agent-mcp-server, an open-source Model Context Protocol server used by AI assistants for local security scans, contains an argument injection vulnerability in its diff scan feature. Specifically, a crafted reference value supplied to the scan is misinterpreted as a command-line option, which bypasses the server's workspace confinement controls. This allows a context-dependent actor to manipulate files arbitrarily on the host system outside the designated workspace directory. The affected versions are >=0.1.1 and <0.2.0.
Potential Impact
An attacker who can supply a crafted reference value to the diff scan operation can create, overwrite, or truncate arbitrary files on the host system outside the intended workspace directory. This bypasses the server's confinement controls and could lead to unauthorized file manipulation, potentially impacting system integrity or availability depending on the files affected.
Mitigation Recommendations
No explicit patch or remediation details are provided in the bulletin. Patch status is not yet confirmed — check the AWS Security Bulletin for the most current remediation guidance. Until a fix is available, avoid using affected versions or restrict access to the diff scan functionality to trusted users only.
Technical Details
- Classification
- {"confidence":0.88,"severitySource":"default","classifier":"rss-v2"}
- Article Source
- {"url":"https://aws.amazon.com/security/security-bulletins/rss/2026-121-aws/","fetched":true,"fetchedAt":"2026-10-01T18:28:34.374Z","wordCount":227}
Threat ID: 6abea652a43b0b3b89e04d4a
Added to database: 10/01/2026, 18:28:34 UTC
Last enriched: 10/01/2026, 18:28:39 UTC
Last updated: 10/02/2026, 03:55:26 UTC
Views: 15
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.