Skip to main content

Agent Zero CVE-2026-51853

| EUVDEUVD-2026-90425 HIGH
Path Traversal (CWE-22)
2026-09-30 mitre GHSA-j6rq-qhh6-gpf5
7.5
CVSS 3.1 · Vendor: mitre
View

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain

  1. Access
    Reach exposed agent-zero web UI
  2. Delivery
    Invoke file browser component
  3. Exploit
    Request path outside intended workspace
  4. Execution
    Read arbitrary host files
  5. Impact
    Exfiltrate credentials and secrets

Vulnerability Assessment

Weakness
CWE
OWASP Top 10:2025
A01:2025 - Broken Access Control
ASVS 5.0
V5 - File Handling Path canonicalization, traversal prevention
MITRE ATT&CK

2 techniques across 2 tactics: Discovery, Collection

The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up.

Exploitation Conditions

The flaw is a default-configuration design defect: FileBrowser.__init__ sets the workspace to the host root directory, so no special feature toggle or non-default setting is required for the agent to reach any file on the system. The principal LIMITING factor is reachability - an attacker must be able to interact with the agent-zero file-browser interface; because agent-zero is frequently run as a local single-operator tool rather than a network-exposed service, the AV:N/PR:N modeling only holds where the UI is deliberately exposed to untrusted networks without an authentication layer. No user interaction and no authentication are required by the supplied vector against affected versions 1.7, 1.8, 1.9, and 1.10.

Impact

Signals are mixed and point to a moderate, not emergency, priority. The supplied CVSS 3.1 vector (AV:N/AC:L/PR:N/UI:N/C:H/I:N/A:N, 7.5) models an unauthenticated network-reachable information-disclosure flaw, but this is a design-level issue (FileBrowser initializes its workspace at the host root), so real exploitability hinges entirely on whether the agent-zero web interface is actually exposed to the attacker - many agent-zero deployments run locally for a single operator, which the AV:N/PR:N vector does not capture. EPSS is low (0.33%, 24th percentile), consistent with a niche open-source target rather than mass exploitation. It is NOT in CISA KEV, so there is no confirmed active exploitation. A public gist (Ro1ME) is referenced alongside the upstream GitHub issue, which strongly suggests exploit/PoC detail is publicly available, though no explicit POC flag was provided in the input - treat exploit-code availability as inferred from the gist reference, not confirmed. Net: a legitimate confidentiality bug worth patching, but the network-vector/no-privileges framing likely overstates risk for the common local-deployment case - verify exposure before prioritizing.

Exploit ScenarioDerived

An attacker who can reach an exposed agent-zero instance (1.7-1.10) uses the agent's file-browser capability, whose workspace is rooted at the host filesystem root rather than a sandboxed directory, to read arbitrary files such as /etc/passwd, SSH keys, or application secrets. A public gist appears to document the technique, lowering the effort required. No authentication or user interaction is modeled in the supplied CVSS vector.

This Week Schedule remediation this week. Why: HIGH severity (CVSS 7.0-8.9).
No patch listed yet 0.3% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Oct 01, 2026

Directory traversal in Agent Zero 1.7 through 1.10 lets the AI agent's file-browser component read files anywhere on the host, because FileBrowser is initialized with the host root as its workspace rather than a confined sandbox. The CVSS 3.1 vector is 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N), which models unauthenticated network access, but the practical risk is gated by whether the Agent Zero UI is exposed to untrusted networks; Agent Zero is often a local single-operator tool, so the AV:N/PR:N rating only applies when that interface is deliberately reachable without an authentication layer. At time of analysis there is no confirmed active exploitation (no CISA KEV entry) and no public exploit identified at time of analysis, and EPSS is 0.33% (24th percentile), indicating low predicted exploitation activity; reference material consists of a GitHub issue and a gist.

RemediationAI

No vendor-released patch identified at time of analysis; the supplied references point to a GitHub issue and a gist rather than a tagged fixed release, so do not assume a version upgrade resolves the issue unless Agent Zero maintainers publish a patched version. Until a patch is available, compensate by never exposing the Agent Zero file-browser interface to untrusted networks: bind it to localhost, place it behind an authenticated reverse proxy or VPN, or block external access at the firewall, with the trade-off that remote usability is reduced. Run Agent Zero under a dedicated unprivileged OS account whose filesystem permissions deny read access to sensitive directories such as /etc, /root, home directories, cloud credential paths, and SSH keys; this may break agent features that expect broad filesystem visibility. Use containers or sandboxing with read-only mounts and only the specific workspace volumes the agent needs, accepting reduced agent functionality. If the file-browser helper is not required, disable or remove the FileBrowser functionality or restrict the agent's tool access so the file-browser path cannot be reached. Monitor for path-traversal patterns and unexpected reads of host files; reference URLs are https://github.com/agent0ai/agent-zero/issues/1539, https://gist.github.com/Ro1ME/4fe09fc7f94c9c0b10c8b6198a70e920, and https://nvd.nist.gov/vuln/detail/CVE-2026-51853.

Affected VersionsENISA

n/a n/a

Affects your stack

Find out whether the stacks and servers you run are on an affected version.

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Technical ContextAI · show details

The flaw is classified as CWE-22 (Improper Limitation of a Pathname to a Restricted Directory, also known as Path Traversal) in Python code at python/helpers/file_browser.py. In Agent Zero 1.7 through 1.10, the FileBrowser.__init__ constructor sets the workspace to the host root directory, so the component's path handling has no confinement boundary to enforce. The underlying issue is a default-configuration design defect rather than a memory-safety bug: file reads through the file-browser interface can resolve to arbitrary host paths. The supplied CPE string is cpe:2.3:a:n/a:n/a:*:*:*:*:*:*:*:* and the EUVD affected-version field is n/a n/a, so product and version identification comes from the description and linked issue rather than structured CPE data. The CVSS 3.1 vector AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N indicates a network-reachable, unauthenticated information-disclosure path with high confidentiality impact and no integrity or availability impact; the independent assessment notes that this vector is only realistic where the file-browser UI is exposed to untrusted networks without an authentication layer.

Know when Python gets its next vulnerability

  • Watch products and get an email when something new is published
  • Check this CVE against your own stack and servers
  • Exploit and PoC references, threat intelligence from 22 sources

No credit card · 7-day full trial

Severity by source

Vendor (mitre) PRIMARY 7.5 HIGH
AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
vuln.today AI 7.5 HIGH

Unauthenticated read of arbitrary files via a reachable web interface gives C:H with no integrity or availability impact; AV:N/PR:N retained per default no-auth exposure.

3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (mitre).

CVSS VectorVendor: mitre

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None

Lifecycle Timeline

3
CVSS changed
Oct 01, 2026 - 19:22 NVD
7.5 (HIGH)
CVE Published
Sep 30, 2026 - 00:00 cve.org
HIGH 7.5
CVE Published
Sep 30, 2026 - 00:00 cve.org
UNKNOWN (no severity yet)

DescriptionCVE.org

agent-zero 1.7, 1.8, 1.9, and 1.10 is vulnerable to Directory Traversal in python/helpers/file_browser.py:FileBrowser.__init__. The FileBrowser class initializes with the host root directory as the workspace, allowing the agent to access any file on the system without restriction.

Executive ViewAI

Why It Matters

Agent Zero versions 1.7 through 1.10 contain a high-severity flaw that could let an attacker read files from the host system through the AI agent's file-browser component, potentially exposing sensitive configuration, credentials, or proprietary data. The risk is most acute for organizations that expose the Agent Zero interface to untrusted networks without an authentication layer, while local single-operator deployments face lower practical exposure. No public exploit has been identified at time of analysis, and no vendor patch is currently available, so leadership should prioritize inventory and exposure reduction while monitoring for vendor guidance.

Business Impact: Medium
Compensating Controls

Restrict Agent Zero UI to trusted networks or localhost; require authentication via reverse proxy or VPN; disable or restrict the file-browser component; run Agent Zero in a least-privileged container or dedicated host with read-only filesystem and no sensitive host mounts; monitor and alert on anomalous file reads; apply vendor patch when released.

Threat Intelligence Overview

EPSS Score
0.3%
Top 76% exploitable
Prevalence
Low
niche open-source AI-agent framework, limited production/enterprise footprint
Data Quality
6 sources
Confidence: High

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue
Severity HIGH
CISA KEV No
Public POC No
EPSS 0.3%
Patch available No
Active threat No
Deciding rule
HIGH severity (CVSS 7.0-8.9)
What every action level means
Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.
Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.
This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.
This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.
Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision
Scheduled
Exploitation
Poc
System Exposure· derived
Open
Automatable
Yes
Human Impact
Medium
Technical Impact
Partial

Priority Score

38
Low Medium High Critical
KEV: 0
EPSS: 0
CVSS: +38
PoC: 0
Weaponized: 0
Threat intel: 0
Gov advisory: 0

Attack Technique

Path traversal exploits occur when applications use user-controlled input to construct file system paths without proper validation.

More in Python

View all
CVE-2025-24016 CRITICAL POC
9.9 Feb 10

Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t

CVE-2025-27520 CRITICAL POC
9.8 Apr 04

BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser

CVE-2025-2945 CRITICAL POC
9.9 Apr 03

pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi

CVE-2013-5093 MEDIUM POC
6.8 Sep 27

The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python

CVE-2025-32375 CRITICAL POC
9.8 Apr 09

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica

CVE-2014-0224 HIGH POC
7.4 Jun 05

OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph

CVE-2024-21644 HIGH POC
7.5 Jan 08

pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.

CVE-2026-33017 CRITICAL POC
9.3 Mar 17

Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301

CVE-2017-9462 HIGH POC
8.8 Jun 06

In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse

CVE-2026-49869 CRITICAL POC
10.0 Jun 26

Unauthenticated remote code execution affects Kestra OSS (the open-source event-driven orchestration platform) prior to

CVE-2026-39987 CRITICAL POC
9.3 Apr 08

Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/

CVE-2024-21645 MEDIUM POC
5.3 Jan 08

pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy