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

Back
New CVE Detected

CVE-2026-82275 – Unauthenticated Arbitrary File Read – Qwen-Agent ≤ 0.0.34

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

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-82275 is a path traversal vulnerability (CWE-22) affecting Qwen-Agent, the open-source LLM application framework maintained by QwenLM, in versions through 0.0.34. The document parser fails to restrict file access to intended directories, allowing an unauthenticated attacker to submit an absolute file path and read arbitrary files accessible to the server process. The flaw carries a CVSS v4.0 base score of 8.7 (High).

Technical details

  • Root cause: The document-parsing tools (SimpleDocParser/DocParser) pass a caller-supplied url/path value directly into file-type detection and file-reading logic (qwen_agent/utils/utils.py and qwen_agent/tools/simple_doc_parser.py) without validating that the resolved path stays within the intended working directory.
  • Trigger conditions: An attacker supplies an absolute local file path (e.g., /etc/passwd) instead of a legitimate document URL/path, either by invoking the parser directly or via the exposed HTTP interface.
  • Attack vector: Network — Qwen-Agent’s Gradio-based service exposes an unauthenticated HTTP endpoint (observed on port 7866) that accepts a JSON request with a task=cache action and a url parameter; this parameter is forwarded to the document parser without authentication or path sanitization.
  • Impact: Full-content disclosure of any file readable by the server process (e.g., /etc/passwd was retrieved in the proof-of-concept), enabling exposure of configuration files, credentials, or other sensitive host data. No integrity or availability impact was demonstrated.

Affected software

  • QwenLM Qwen-Agent (PyPI package qwen-agent) — all versions 0 through 0.0.34 (inclusive)

Severity

  • CVSS v3.1: 7.5 (HIGH) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
  • CVSS v4.0: 8.7 (HIGH) — 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
  • CWE-22: Improper Limitation of a Pathname to a Restricted Directory (‘Path Traversal’)

Mitigation and recommended actions

  • Immediate: No fixed release has been published as of this writing; monitor the QwenLM/Qwen-Agent GitHub repository for a patched version and upgrade as soon as one is available.
  • Workarounds / network mitigations (until a patch is released):
    • Do not expose the Qwen-Agent Gradio/HTTP interface (including the document-cache endpoint) directly to untrusted networks or the internet; bind it to localhost or place it behind authentication and network access controls.
    • Reject document requests containing absolute file paths or file:// schemes that resolve outside the configured work_dir/workspace directory.
    • Run the Qwen-Agent server process with least-privilege file system permissions to limit the blast radius of any unauthorized file read.
    • Deploy the service behind a reverse proxy/WAF that enforces authentication on all API endpoints.

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