Skip to content

Command Injection via code search tool arguments

High
Legoben published GHSA-8r78-7jwh-m6hm Jun 9, 2026

Package

Warp

Affected versions

>=v0.2025.04.09.08.11.stable_00

Patched versions

v0.2026.05.06.15.42.stable_01

Description

Description

Impacted Warp versions contain a command execution policy bypass in Agent code search tools. The affected Grep and FileGlob actions are authorized as read/search operations, but their implementations build shell command strings from Agent-controlled inputs (search text, paths, glob patterns) and execute them in the active terminal session

Impact

An attacker who can influence Agent context or tool arguments, such as through malicious project instructions or prompt-injected local content, can cause a search action that appears read-only to execute shell syntax. This bypasses the command execution approval and allow/deny policy that would apply to an explicit command-running tool.

The resulting command runs with the privileges of the active Warp session. Exploitation requires user interaction: the user must invoke Warp Agent against attacker-influenced content.

Patch

The patch quotes complete search arguments, paths, and glob patterns as shell data before building the generated command strings, including PowerShell-specific handling.

Workarounds

Update to a patched Warp version. More intelligent models are typically more capable of resisting this kind of attack.

Credits

Thanks to the following reporters who responsibly disclosed this issue:

References

Severity

High

CVSS overall score

This score calculates overall vulnerability severity from 0 to 10 and is based on the Common Vulnerability Scoring System (CVSS).
/ 10

CVSS v3 base metrics

Attack vector
Local
Attack complexity
Low
Privileges required
None
User interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

CVSS v3 base metrics

Attack vector: More severe the more the remote (logically and physically) an attacker can be in order to exploit the vulnerability.
Attack complexity: More severe for the least complex attacks.
Privileges required: More severe if no privileges are required.
User interaction: More severe when no user interaction is required.
Scope: More severe when a scope change occurs, e.g. one vulnerable component impacts resources in components beyond its security scope.
Confidentiality: More severe when loss of data confidentiality is highest, measuring the level of data access available to an unauthorized user.
Integrity: More severe when loss of data integrity is the highest, measuring the consequence of data modification possible by an unauthorized user.
Availability: More severe when the loss of impacted component availability is highest.
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CVE ID

CVE-2026-48703

Weaknesses

Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component. Learn more on MITRE.

Credits