agentscope-ai AgentScope up to 2.0.7.post1 LocalWorkspace LocalWorkspace.add_skill skill_path path traversal

Summaryinfo

A vulnerability categorized as problematic has been discovered in agentscope-ai AgentScope up to 2.0.7.post1. This affects the function LocalWorkspace.add_skill of the component LocalWorkspace. Such manipulation of the argument skill_path leads to path traversal. This vulnerability is referenced as CVE-2026-85685. It is possible to launch the attack remotely. No exploit is available.

Detailsinfo

A vulnerability was found in agentscope-ai AgentScope up to 2.0.7.post1 and classified as problematic. Affected by this issue is the function LocalWorkspace.add_skill of the component LocalWorkspace. The manipulation of the argument skill_path with an unknown input leads to a path traversal vulnerability. Using CWE to declare the problem leads to CWE-22. 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. Impacted is confidentiality. CVE summarizes:

AgentScope through 2.0.7.post1 contains a path traversal vulnerability in LocalWorkspace.add_skill that copies arbitrary server directories into the agent workspace via an unconfined source path parameter. Attackers can supply any directory path in the skill_path request parameter to copy files into the skills directory, making them accessible through the workspace skill listing.

The advisory is shared for download at github.com. This vulnerability is handled as CVE-2026-85685 since 09/04/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. There are known technical details, but no exploit is available. The current price for an exploit might be approx. USD $0-$5k (estimation calculated on 09/04/2026). The MITRE ATT&CK project declares the attack technique as T1006.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Productinfo

Type

• Artificial Intelligence Software

Vendor

• agentscope-ai

Name

• AgentScope

Version

• 2.0.7.post1

Website

• Product: https://github.com/agentscope-ai/agentscope/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Discussion