CVE-2025-55284Network attack vector

File exfiltration via permissive safe-command allowlist

Published Aug 16, 2025 · Updated Aug 18, 2025

OS command injection in Claude Code before 1.0.4 allows remote attackers to read local files and exfiltrate them over the network. The default safe-command allowlist is overly broad, allowing attacker-influenced context to select commands that bypass confirmation for file access and outbound transmission. Exploitation requires untrusted content in the context window and discloses file contents without reported modification or service interruption.

CVSS severity7.1
High
EPSS probability0.46%
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

OS command injection in Claude Code before 1.0.4 allows remote attackers to read local files and exfiltrate them over the network. The default safe-command allowlist is overly broad, allowing attacker-influenced context to select commands that bypass confirmation for file access and outbound transmission. Exploitation requires untrusted content in the context window and discloses file contents without reported modification or service interruption.

The record

CVE
CVE-2025-55284
Published
Aug 16, 2025
Updated
Aug 18, 2025
Vendor
Anthropic
Product
Claude Code
Classifications
CWE-78, CAPEC-88, T1005
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Aug 16, 2025CVE publishedPublication date reported by the CVE source.
  2. Aug 18, 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=< 1.0.4

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Anthropic · Claude Codeversion=< 1.0.4

Published CVSS scores

7.1GitHubCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

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 exploitUnconfirmed

Weakness, pattern, technique

CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
CAPEC-88OS Command Injection
T1005Data from Local System

Public exploit references

No public exploit references are available in this record.

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