CVE-2025-54794

criticalpriority · attend · 46EPSS 0.014 · 71 %ileexploit · PoCEURUUS

grimoire priorityP1 · Urgent

Exploitable?

Public exploit

1 exploit · PoC

Likely / severe?

1.36% (71st) EPSS

CVSS 9.1 · critical

Is it mine?

4 products

Check your exposure

Who says so?

5 sources

cnnvd · enisa_euvd · fstec_bdu · nvd

EPSS · scored 2026-10-23

Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of (or ability to create) a directory with the same prefix as the CWD and the ability to add untrusted content into a Claude Code context window. This is fixed in version 0.2.111.

cvss

Technical severity, 0–10. One row per scoring source.

9.1

010

base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–critical · 6.8–9.1

v3.19.1criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Nprimary · NVD / NIST USexploitability 3.9 · impact 5.2

v3.18.8highAV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:Hsecondary · FSTEC (BDU) RU

v4.07.7highCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:Nsecondary · ENISA EU

v4.07.7highCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · security-advisories@github.com

v4.06.8mediumCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:Xsecondary · CVSS-BT (t0sche)

ssvc

A stakeholder decision — act, attend, or track — from exploitation and impact.

Exploitation: none · Automatable: no · Technical Impact: totalcoordinatorcisa_ssvcUS

weaknesses

The CWE weakness classes this flaw belongs to.

CWE-22USCWE-22USCWE-22US

exploits (1)

Public proof-of-concept and weaponised exploit code.

AdityaBhatt3010/CVE-2025-54794-Hijacking-Claude-AI-with-a-Prompt-Injection-The-Jailbreak-That-Talked-BackA high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of code.PoC · poc_in_github

affected products (4)

Products and version ranges known to be affected.

anthropics claude-code≤ < 0.2.111enisa_euvdEU
Anthropic Claude Code≤ 0.2.111fstec_bduRU
anthropic claude code< 0.2.111nvdUScpe:2.3:a:anthropic:claude_code:*:*:*:*:*:*:*:*
npm @anthropic-ai/claude-code< 0.2.111osvUSpkg:npm/%40anthropic-ai/claude-code

advisories (1)

Vendor and ecosystem advisories describing this.

GHSA-pmw4-pwvc-3hx2Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access2025-08-04ghsa · osvUS
Due to a path validation flaw using prefix matching instead of canonical path comparison, it was possible to bypass directory restrictions and access files outside the CWD. Successful exploitation depends on the presence of (or ability to create) a directory with the same prefix as the CWD and the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update. Thank you to Elad Beber (Cymulate) for reporting this issue!

also known as (4)

Other names and identifiers for this entity.

sources

Which sources assert this record, and when.

cnnvd enisa_euvd fstec_bdu nvd osv NVD CVE.org MITRE

published 2025-08-05modified 2026-06-17

references (5)

External citations — patches, advisories, analysis.

scry

Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.

Free scan