Skip to content

Repository navigation

Sandbox path traversal in Cline harness file tools

High
dnukumamras published GHSA-222v-gj5h-ff73 Aug 20, 2026

Package

npm @ai-sdk/harness-cline (npm)

Affected versions

>= 1.0.0, < 1.0.8

Patched versions

1.0.8

Description

Summary

@ai-sdk/harness-cline versions 1.0.0 through 1.0.7 did not properly restrict paths supplied to the Cline harness file tools to the session working directory.

Model-controlled absolute paths and paths containing traversal sequences could escape the workspace through the built-in read, write, edit, grep, glob, and ls tools. Symlinks resolving outside the allowed roots were also not adequately contained.

Impact

An attacker who can influence model input or output, such as through prompt injection, could cause the harness to read files outside the current session working directory without an approval prompt. This could expose files belonging to concurrent sessions, including environment variables, credentials, configuration, and agent state.

When the harness is operating in allow-edits mode, the attacker could also write to or modify files outside the current workspace. In environments where sessions share a sandbox, this could enable cross-session workspace poisoning.

Exploitation requires an application to use the Cline harness file tools and for the attacker to successfully steer the model into invoking a tool with a malicious path.

Patches

The issue is fixed in @ai-sdk/harness-cline 1.0.8.

The fix normalizes requested paths, resolves their sandbox-side real paths, and rejects paths outside the session working directory or explicitly configured readable roots. Writable operations remain restricted to the session working directory, and recursive searches no longer follow symlinks.

Users should upgrade to version 1.0.8 or later.

Workarounds

Until an upgrade is possible, avoid using the Cline harness file tools with untrusted or attacker-controlled content.

Run each agent session in an isolated sandbox that does not contain credentials or files belonging to other sessions. Disabling allow-edits reduces the integrity impact but does not prevent unauthorized reads.

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 v4 base metrics

Exploitability Metrics
Attack Vector Network
Attack Complexity Low
Attack Requirements Present
Privileges Required None
User interaction Passive
Vulnerable System Impact Metrics
Confidentiality High
Integrity High
Availability High
Subsequent System Impact Metrics
Confidentiality None
Integrity None
Availability None

CVSS v4 base metrics

Exploitability Metrics
Attack Vector: This metric reflects the context by which vulnerability exploitation is possible. This metric value (and consequently the resulting severity) will be larger the more remote (logically, and physically) an attacker can be in order to exploit the vulnerable system. The assumption is that the number of potential attackers for a vulnerability that could be exploited from across a network is larger than the number of potential attackers that could exploit a vulnerability requiring physical access to a device, and therefore warrants a greater severity.
Attack Complexity: This metric captures measurable actions that must be taken by the attacker to actively evade or circumvent existing built-in security-enhancing conditions in order to obtain a working exploit. These are conditions whose primary purpose is to increase security and/or increase exploit engineering complexity. A vulnerability exploitable without a target-specific variable has a lower complexity than a vulnerability that would require non-trivial customization. This metric is meant to capture security mechanisms utilized by the vulnerable system.
Attack Requirements: This metric captures the prerequisite deployment and execution conditions or variables of the vulnerable system that enable the attack. These differ from security-enhancing techniques/technologies (ref Attack Complexity) as the primary purpose of these conditions is not to explicitly mitigate attacks, but rather, emerge naturally as a consequence of the deployment and execution of the vulnerable system.
Privileges Required: This metric describes the level of privileges an attacker must possess prior to successfully exploiting the vulnerability. The method by which the attacker obtains privileged credentials prior to the attack (e.g., free trial accounts), is outside the scope of this metric. Generally, self-service provisioned accounts do not constitute a privilege requirement if the attacker can grant themselves privileges as part of the attack.
User interaction: This metric captures the requirement for a human user, other than the attacker, to participate in the successful compromise of the vulnerable system. This metric determines whether the vulnerability can be exploited solely at the will of the attacker, or whether a separate user (or user-initiated process) must participate in some manner.
Vulnerable System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the VULNERABLE SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the VULNERABLE SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the VULNERABLE SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
Subsequent System Impact Metrics
Confidentiality: This metric measures the impact to the confidentiality of the information managed by the SUBSEQUENT SYSTEM due to a successfully exploited vulnerability. Confidentiality refers to limiting information access and disclosure to only authorized users, as well as preventing access by, or disclosure to, unauthorized ones.
Integrity: This metric measures the impact to integrity of a successfully exploited vulnerability. Integrity refers to the trustworthiness and veracity of information. Integrity of the SUBSEQUENT SYSTEM is impacted when an attacker makes unauthorized modification of system data. Integrity is also impacted when a system user can repudiate critical actions taken in the context of the system (e.g. due to insufficient logging).
Availability: This metric measures the impact to the availability of the SUBSEQUENT SYSTEM resulting from a successfully exploited vulnerability. While the Confidentiality and Integrity impact metrics apply to the loss of confidentiality or integrity of data (e.g., information, files) used by the system, this metric refers to the loss of availability of the impacted system itself, such as a networked service (e.g., web, database, email). Since availability refers to the accessibility of information resources, attacks that consume network bandwidth, processor cycles, or disk space all impact the availability of a system.
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVE ID

No known CVE

Weaknesses

Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. Learn more on MITRE.

UNIX Symbolic Link (Symlink) Following

The product, when opening a file or directory, does not sufficiently account for when the file is a symbolic link that resolves to a target outside of the intended control sphere. This could allow an attacker to cause the product to operate on unauthorized files. Learn more on MITRE.