VulnSocial

CVE-2025-66032Patch(anthropic / claude_code)

LOWCVSS 9.8 · CRITICAL

Signal is active with 1 mentions in latest observed window

Immediate actions

  • Patch anthropic claude_code systems immediately

Recommended action window: Monitor and triage in normal cycle

NVD description

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.

anthropic CVEsBack to dashboard
0.5/ 10 priority

Sources & remediation

Vendor / third-party advisories
Weakness type (CWE)
CWE-77

Priority

LOW

Exploitation

NONE

PoC

NONE

Patch

AVAILABLE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

  • claude_code

Threat summary

  • Patch or workaround signal is available
  • 2 mentions across 2 observed days
  • Momentum state: stable

What's happening

  • Patch or workaround mentioned in 1 signal
  • Technical details provided in 1 signal
  • Disclosure: 1 classified signal
  • Peaked 1d ago at 1 mentions (2026-01-31); latest day: 1
  • 2 total mentions across 2 days

Affected systems

Vendors
anthropic
Products
claude_code

Deep dive

Activity timeline2 mentions / 2d
00111Mentions · 2026-01-31: 1Mentions · 2026-08-05: 1Patch / Workaround · 2026-01-31: 1Technical Details · 2026-08-05: 101-3108-05
Signal classification2 categories
Patch
150.0%
Disclosure
150.0%
Classification over time
DateTotalLabels
2026-01-311
Patch1
2026-08-051
Disclosure1
Full discourse2 posts
  • Tosin Afolabi@Tosin_afolabi09
    Disclosure

    In Dec 2025 a shell-parsing bug in Claude Code let untrusted text in the context window execute arbitrary code. CVE-2025-66032, CVSS 9.8. The security boundary was a parser deciding if a command was read-only. It lost to $IFS quoting. https://t.co/bC7VnbrM9h

    Post summary

    The tweet announces a high‑severity shell parsing vulnerability (CVE-2025‑66032) in Claude Code, describing the bug’s mechanics but providing no PoC, exploit code, patch, or evidence of active exploitation.

    1001331.4K
    69 followersView on X
  • קודקוד סייבר@kodkodcyber
    Patch

    חולשות אלו קיבלו את ה-CVE-2025-66032 ותוקנו בגרסת 1.0.93 של Claude Code. וכמו כל חולשה שמתגלת בכלי AI, היא מחדדת את החשיבות של אי שימוש עיוור בכלי AI, מעבר בסיסי על הקוד לפני שימוש בכלים על קוד לא ידוע מ-Github ובעיקר, מודעות לסכנות. https://t.co/TNFI4zO7oX

    Post summary

    CVE‑2025‑66032 was discovered, but a patch was released in version 1.0.93 of Claude Code, and no exploit or PoC was mentioned.

    00030203
    2.1K followersView on X
CPE platform detail1 entries

1 of 1 entries

PartVendorProductVersionTarget SWTarget HW
Appanthropicclaude_code-node.js-

Explore more

Back to dashboardanthropic CVEsclaude_code vulnerabilities