Skip to main content
EPSS 0.5%top 55%

CVE-2026-85685: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in agentscope-ai agentscope

0
High
VulnerabilityCVE-2026-85685cvecve-2026-85685
Published: 09/04/2026 (09/04/2026, 14:32:31 UTC)
Source: CVE Database V5
Vendor/Project: agentscope-ai
Product: agentscope

Description

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.

CVSS v4.0

Score 8.7high

Attack Vector
Network
Attack Complexity
Low
Attack Requirements
None
Privileges Required
None
User Interaction
None
Vuln. Confidentiality
High
Vuln. Integrity
None
Vuln. Availability
None
Subsq. Confidentiality
None
Subsq. Integrity
None
Subsq. Availability
None
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Affected software

agentscope-ai

agentscope

Affected versions
>=0 <=2.0.7.post1

AI-Powered Analysis

Machine-generated threat intelligence

AILast updated: 09/07/2026, 12:16:03 UTC

Technical Analysis

CVE-2026-85685 is a path traversal vulnerability in agentscope-ai's agentscope product affecting versions up to 2.0.7.post1. The vulnerability exists in the LocalWorkspace.add_skill method, which copies files from a source path specified by the skill_path parameter into the agent workspace. Because the source path is not properly restricted, an attacker can supply arbitrary directory paths to copy files from anywhere on the server into the skills directory, making them accessible via the workspace skill listing. This can lead to unauthorized disclosure of sensitive server files. The vulnerability is remotely exploitable without authentication or user interaction, resulting in a high CVSS 4.0 score of 8.7.

Potential Impact

An unauthenticated attacker can exploit this vulnerability to copy arbitrary files from the server into the agent workspace's skills directory, potentially exposing sensitive server files through the skill listing interface. This unauthorized file access can lead to information disclosure and may aid further attacks depending on the contents of the exposed files.

Mitigation Recommendations

Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, avoid exposing the affected functionality to untrusted users or restrict access to trusted environments only.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
VulnCheck
Date Reserved
2026-09-04T13:51:42.563Z
Cvss Version
4.0
State
PUBLISHED

Threat ID: 6a9adb47acd9273b49bef5cb

Added to database: 09/04/2026, 14:52:55 UTC

Last enriched: 09/07/2026, 12:16:03 UTC

Last updated: 10/19/2026, 18:48:24 UTC

Views: 83

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

Need more coverage?

Upgrade to Pro Console for AI refresh and higher limits.

For incident response and remediation, OffSeq services can help resolve threats faster.

Latest Threats

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses