CVE-2025-59536Public exploitNetwork attack vector

Arbitrary command execution via auto-approved project MCP servers

Published Oct 3, 2025 · Updated Oct 3, 2025

Code injection in Anthropic Claude Code before 1.0.111 allows remote attackers to execute arbitrary commands from a crafted project. Repository-controlled .claude/settings.json options auto-approve MCP servers declared in .mcp.json, causing their initialization commands to run before the startup trust dialog. Exploitation requires a user to start Claude Code in the attacker-controlled directory, after which commands run with that user's privileges.

CVSS severity8.7
High
EPSS probability26.36%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Code injection in Anthropic Claude Code before 1.0.111 allows remote attackers to execute arbitrary commands from a crafted project. Repository-controlled .claude/settings.json options auto-approve MCP servers declared in .mcp.json, causing their initialization commands to run before the startup trust dialog. Exploitation requires a user to start Claude Code in the attacker-controlled directory, after which commands run with that user's privileges.

The record

CVE
CVE-2025-59536
Published
Oct 3, 2025
Updated
Oct 3, 2025
Vendor
Anthropic
Product
Claude Code
Classifications
CWE-94, T1204.002, T1059
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Oct 3, 2025CVE publishedPublication date reported by the CVE source.
  2. Oct 3, 2025Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=< 1.0.111

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Anthropic · Claude Codeversion=< 1.0.111

Published CVSS scores

8.7GitHub, Inc.CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
8.8NIST NVDCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitPublished

Weakness, pattern, technique

CWE-94Improper Control of Generation of Code ('Code Injection')
T1204.002Malicious File
T1059Command and Scripting Interpreter

Public exploit references

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo