CVE Feed

    Dashboard / CVE / CVE-2025-55319

    CVE-2025-55319

    Ai command injection in Agentic AI and Visual Studio Code allows an unauthorized attacker to execute code over a network.

    Published:Sep 12, 2025
    Last Modified:Feb 26, 2026
    EPS:Sep 12, 2025
    EPSS Score:0.00073
    CVSS Score:8.8

    Affected Products

    Vendor
    Microsoft
    Product
    Visual Studio Code

    Exploits

    https://github.com/nephila016/CVE-2025-55319-PoC

    Related CVEs

    CVE-2026-81383 (CVSS 7.4) — Use of incorrectly-resolved name or reference in Visual Studio Code allows an unauthorized attacker to disclos…
    CVE-2026-78462 (CVSS 8.8) — Authorization bypass through user-controlled key in Visual Studio Code allows an unauthorized attacker to bypa…
    CVE-2026-81381 (CVSS 6.5) — Insufficiently protected credentials in GitHub Copilot and Visual Studio Code allows an unauthorized attacker …
    CVE-2026-81380 (CVSS 5.3) — Improper neutralization of special elements used in a command ('command injection') in GitHub Copilot and Visu…
    CVE-2026-81379 (CVSS 8.2) — Not failing securely ('failing open') in Visual Studio Code allows an unauthorized attacker to bypass a securi…
    CVE-2026-81378 (CVSS 8.2) — Interpretation conflict in Visual Studio Code allows an unauthorized attacker to bypass a security feature ove…
    CVE-2026-81377 (CVSS 6.5) — Improper limitation of a pathname to a restricted directory ('path traversal') in Visual Studio Code allows an…
    CVE-2026-81376 (CVSS 9.6) — Incomplete comparison with missing factors in Visual Studio Code allows an unauthorized attacker to bypass a s…
    CVE-2026-81357 (CVSS 8.2) — Server-side request forgery (ssrf) in Visual Studio Code allows an unauthorized attacker to bypass a security …
    CVE-2026-81356 (CVSS 8.2) — Inconsistent interpretation of http requests ('http request/response smuggling') in Visual Studio Code allows …

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High