Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-85685 – Unauthenticated Arbitrary Directory Disclosure via Path Traversal – AgentScope ≤ 2.

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-85685 is a path traversal vulnerability (CWE-22) in AgentScope’s LocalWorkspace.add_skill function that allows an attacker to copy arbitrary directories from the host filesystem into an agent’s workspace. Because the copied files are then exposed through the workspace’s skill listing, a remote, unauthenticated attacker can use this flaw to disclose sensitive server files. The issue affects AgentScope through version 2.0.7.post1 and is rated High severity (8.7).

Technical details

  • Root cause: LocalWorkspace.add_skill() confines the destination path to the skills directory but does not validate that the source path (skill_path) supplied by the caller resides inside any allowed root.
  • Trigger condition: An attacker sends a request (e.g., a POST to the workspace skill endpoint) supplying an arbitrary skill_path pointing to any directory on the server that contains a SKILL.md file; AgentScope copies that directory’s contents into the agent’s skills folder.
  • Attack vector: Network-reachable AgentScope workspace/HTTP API; the API’s authentication is described as a placeholder that reads an X-User-ID header, allowing a caller to assert any identity, effectively enabling unauthenticated exploitation.
  • Impact: Disclosure of files copied from outside the intended workspace root — potentially configuration files, credentials, or other tenants’ workspace data — once retrieved via the workspace’s skill listing. No integrity or availability impact has been reported.

Affected software

  • AgentScope (PyPI package agentscope), versions up to and including 2.0.7.post1

Severity

  • CVSS v3.1: 7.5 — AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
  • CVSS v4.0: 8.7 — AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Mitigation and recommended actions

  • Immediate: No vendor-confirmed patched release addressing this CVE by version number has been identified at time of writing; check the AgentScope repository and release notes for an update to LocalWorkspace.add_skill (later releases have made related changes to skill-directory handling) and upgrade as soon as a fix is confirmed.
  • If no patch is available: Restrict network access to the AgentScope workspace/HTTP API to trusted hosts only, do not expose the workspace API directly to the internet, replace or front the placeholder X-User-ID-based authentication with proper authentication/authorization, and validate/deny any skill_path values that resolve (via realpath) outside the intended skills root or contain traversal sequences.

How IONIX identifies potentially affected assets

IONIX matches the following signals against data already collected when it crawled the asset; identifying the technology sends no request beyond that crawl.

  • Page title: AgentScope Studio, AgentScope

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge