Code execution via agentic command injection
Published Sep 12, 2025 · Updated Sep 12, 2025
AI command injection in Microsoft Visual Studio Code before 1.104.0 allows remote attackers to execute code through agent mode. Microsoft has not published the vulnerable function or command-construction path; release notes identify untrusted Internet content as a prompt-injection vector for agent-issued terminal commands. Exploitation requires user interaction and an agent session that processes attacker-controlled content, after which commands run with the local user's privileges.
Summary
What happened
AI command injection in Microsoft Visual Studio Code before 1.104.0 allows remote attackers to execute code through agent mode. Microsoft has not published the vulnerable function or command-construction path; release notes identify untrusted Internet content as a prompt-injection vector for agent-issued terminal commands. Exploitation requires user interaction and an agent session that processes attacker-controlled content, after which commands run with the local user's privileges.
The record
- CVE
- CVE-2025-55319
- Published
- Sep 12, 2025
- Updated
- Sep 12, 2025
- Vendor
- Microsoft
- Product
- Visual Studio Code
- Classifications
- CWE-77, T1059
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 12, 2025CVE publishedPublication date reported by the CVE source.
- Sep 12, 2025Record 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=1.0.0 <1.104.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
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.
Weakness, pattern, technique
Public exploit references
- CVE-2025-55319 PoC VS Code extensionproof of concept · unverified
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
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo