# CVE-2025-66032 — anthropics claude-code

> As of 2025-12-03, CVE-2025-66032 is a High-severity (band derived from the CVSS v4.0 score, not stated by the CNA) vulnerability in anthropics claude-code, CVSS v4.0 8.7, EPSS 0.6% (51.2th percentile). Threadlinqs Intelligence links 1 tracked threat campaign to CVE-2025-66032, most recently “Fake Bug Report Prompt Injection Attacks Hijacking AI Coding Agents (Agentjacking)”.

**Last updated:** 2025-12-03

## What is CVE-2025-66032?

Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 1.0.93.

The record classifies CVE-2025-66032 under weakness class [CWE-77](https://intel.threadlinqs.com/cwe/CWE-77). 1 affected-product entry is recorded, across 1 vendor, listed below. The identifier was first published 311 days ago.

## Severity and exploitation probability

- **CVSS v4.0 base score:** 8.7 — High (derived from score) (`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`)
- **EPSS (FIRST):** 0.6% probability of exploitation in the next 30 days, higher than 51.2% of all scored CVEs
- **CISA KEV:** Not listed in the CISA Known Exploited Vulnerabilities catalog
- **Threadlinqs priority:** 6.4/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability
- **Published:** 2025-12-03

## Is CVE-2025-66032 being exploited?

It currently carries a trending score of 18 in the Threadlinqs vulnerability feed.

## Affected products and versions

- [anthropics](https://intel.threadlinqs.com/vendors/anthropics): claude-code

## How to fix CVE-2025-66032

No vendor patch reference has been recorded for CVE-2025-66032 in the tracked sources. Follow the references below for a fix, and treat the products listed above as exposed until the vendor states otherwise.

## Threat activity tracking CVE-2025-66032

1 tracked threat in the Threadlinqs corpus references CVE-2025-66032, either in the campaign’s CVE list or as an indicator on the campaign record.

- [Fake Bug Report Prompt Injection Attacks Hijacking AI Coding Agents (Agentjacking)](https://intel.threadlinqs.com/threat/TL-2026-1012) — CRITICAL · 2026-06-30

## Sources

Enriched from CVE.org, FIRST EPSS. Last verified by Threadlinqs on 2026-10-10.

**Vendor advisory and patch**

- [github.com](https://github.com/anthropics/claude-code/security/advisories/GHSA-xq4m-mc3c-vvg3)

Canonical: https://intel.threadlinqs.com/cve/CVE-2025-66032
Full detection coverage and IOCs for threats exploiting CVE-2025-66032 via the Threadlinqs MCP server (Purple tier): https://intel.threadlinqs.com/mcp