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. 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: 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) — CRITICAL · 2026-06-30
Sources
Enriched from CVE.org, FIRST EPSS. Last verified by Threadlinqs on .