CVE-2025-54794
Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access
Description
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.
INFO
Published Date :
Aug. 5, 2025, 1:15 a.m.
Last Modified :
Oct. 27, 2025, 6:01 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 4.0 | HIGH | [email protected] |
Solution
- Update Claude Code to version 0.2.111.
- Review directory access controls.
- Sanitize untrusted content input.
Public PoC/Exploit Available at Github
CVE-2025-54794 has a 22 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2025-54794.
| URL | Resource |
|---|---|
| https://github.com/anthropics/claude-code/security/advisories/GHSA-pmw4-pwvc-3hx2 | Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2025-54794 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2025-54794
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Open Autonomous Coding-agent Baseline — security framework for Claude Code autonomous mode. OWASP ASI 2026 + MITRE ATLAS mapped. Apache 2.0.
Shell JavaScript
None
None
Python Shell JavaScript
parrotagent.github.io
HTML
Hybrid classical + post-quantum (NIST FIPS 204 ML-DSA-65) digital receipts for AI agent decisions. First production MCP server with offline-verifiable post-quantum signing.
ai-agents ai-safety cnsa-2 cryptographic-receipts cryptography crystals-dilithium ed25519 eu-ai-act fips-204 mcp ml-dsa-65 model-context-protocol owasp-asi post-quantum-cryptography prompt-injection-defense python responsible-ai agentic-diffusion cve-2026-25253 trustatom
Python
Hardened PreToolUse hooks for Claude Code, Cursor, and OpenClaw. Blocks pipe-to-shell, reverse shells, credential exfil, and destructive commands. Because settings.json deny rules have been broken across 4 versions.
Shell
Sentinel Skill for Claude
Python
Agentic DevSecOps for Claude Code. Token-efficient security framework defending against prompt injection, MCP exfiltration, supply chain attacks, and compaction laundering.
PowerShell Python
Open-source cross-modal and multimodal prompt injection test suite. 250,000+ attack payloads across text, image, document, and audio modalities. Research-backed by OWASP LLM Top 10, CrossInject (ACM MM 2025), FigStep (AAAI 2025), DolphinAttack, and CSA 2026.
Python Shell
A curated timeline of real AI agent security incidents, breaches, and vulnerabilities (2024-2026). Every entry sourced and dated.
ai-agent-security ai-agents ai-security awesome-list cybersecurity llm-security mcp-security prompt-injection supply-chain-security adversarial-attacks agent-security agentic-ai ai-attacks ai-safety cve incident-response owasp red-team security-research vulnerability
Detection rules for the Claude Code source leak : 16 Sigma rules, Splunk, Elastic, YARA. Lab-validated on GOAD Light DC02.
claude-code elastic mitre-attack sigma splunk supply-chain-attack sysmon yara
YARA Python Shell PowerShell
Nix portable security hardened Claude Sandbox with restrictive whitelist & blacklist policies
Nix Shell Python
None
Shell
None
Shell Python JavaScript HTML CSS TypeScript Dockerfile Gherkin
None
Python Shell JavaScript HTML
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2025-54794 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2025-54794 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
Initial Analysis by [email protected]
Oct. 27, 2025
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N Added CPE Configuration OR *cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* versions up to (excluding) 0.2.111 Added Reference Type GitHub, Inc.: https://github.com/anthropics/claude-code/security/advisories/GHSA-pmw4-pwvc-3hx2 Types: Vendor Advisory -
New CVE Received by [email protected]
Aug. 05, 2025
Action Type Old Value New Value Added Description 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. Added CVSS V4.0 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:X Added CWE CWE-22 Added Reference https://github.com/anthropics/claude-code/security/advisories/GHSA-pmw4-pwvc-3hx2