How severe is CVE-2026-33068?

No CVSS score has been assigned to CVE-2026-33068 yet. Review the advisory details and affected package list to assess your exposure.

Which packages are affected by CVE-2026-33068?

CVE-2026-33068 affects the following packages: @anthropic-ai/claude-code (npm). Ecosystems affected: npm.

How do I fix CVE-2026-33068?

Update @anthropic-ai/claude-code to 2.1.53 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-33068 is resolved across your whole dependency graph.

How do I detect CVE-2026-33068 in my npm dependencies?

Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

How do I mitigate CVE-2026-33068 if there is no patch (or I can't update yet)?

If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Is CVE-2026-33068 actively exploited in the wild?

No public exploit code has been indexed for CVE-2026-33068 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2026-33068?

CVE-2026-33068 has an EPSS (Exploit Prediction Scoring System) score of 0.4%, placing it in the 29th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is CVE-2026-33068?

CVE-2026-33068 is classified as CWE-807 (CWE-807). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation.

When was CVE-2026-33068 published, and has it been updated?

CVE-2026-33068 was published on March 20, 2026 and was last updated on October 28, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

📦 npm

Not in CISA KEV

CVE-2026-33068 — @anthropic-ai/claude-code

CVE-2026-33068 is a CWE-807 vulnerability in @anthropic-ai/claude-code. A fix is available for @anthropic-ai/claude-code — see the affected versions and patch details below.

Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Also known asGHSA-mmgp-wc2j-qcv7

Published

Mar 20, 2026

Updated

Oct 28, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Nov 8, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

A successful exploit gives an attacker total control of the affected component, not partial access.
CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-33068.

EPSS Exploitation Probability

via FIRST.org ↗

0.4%probability of exploitation in next 30 days

Lower Risk+0.01%

Lower risk than most CVEs29th percentile — riskier than 29% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

Real-World Exposure

1 pkg affected

How broadly this vulnerability is actually deployed: weekly install volume shows current usage, and reverse-dependency count shows how many other packages break if it stays unpatched.

281other npm packages depend on this — each one inherits the vulnerability until it's patched upstream

@anthropic-ai/claude-codenpm

14.2Mdownloads / week

Description

Claude Code resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.

Thank you to hackerone.com/cantina_xyz for reporting this issue.

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
📦npm	`@anthropic-ai/claude-code`	all versions	2.1.53`npm install @anthropic-ai/claude-code@2.1.53`

Affected Products

1 product · 1 configurations

Application

claude codeanthropic

< 2.1.53

range

Detection & mitigation playbook

Open-source dependency

Detect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for @anthropic-ai/claude-code, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update @anthropic-ai/claude-code to 2.1.53 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-33068 is resolved across your whole dependency graph.
Workarounds
If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Frequently Asked Questions

Claude Code resolved the permission mode from settings files, including the repo-controlled `.claude/settings.json`, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set `permissions.defaultMode` to `bypassPermissions` in its committed `.claude/settings.json`, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. Users

O3 Security · Impact-Aware SCA

Is CVE-2026-33068 in your dependencies?

Find it across npm, including transitive dependencies.

Scan my dependencies How O3 SCA works