> CVE-2026-33068 [HIGH]

« BACK_TO_HOME
PUBLISHED
2026-03-20 09:16
MODIFIED
2026-03-20 09:16
CVSS_SCORE V3
7.7
EPSS (Prob. Exploit)
0.59%
Top 52.2%
DATA SOURCES:
NVD đź”— 2026-03-20 CWE MITRE đź”— 2026-11-01 FIRST EPSS đź”— 2026-10-25 GITHUB đź”— 2026-11-05 OSV đź”— 2026-07-26

> DESCRIPTION

Claude Code is an agentic coding tool. Versions prior to 2.1.53 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. This issue has been patched in version 2.1.53.

> AFFECTED_PRODUCTS

ℹ️ Aucun produit affecté n'a encore été publié par NVD pour cette CVE.

> CVSS V3 METRICS

CVSS_VECTOR
CVSS:4.0/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

> MÉTRIQUES CVSS DÉTAILLÉES

CVSS:4.0/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
Métrique Valeur Interprétation
AV (Vecteur d'Attaque)
Attack Vector
Network (N)
Exploit possible à distance via réseau (HTTP, API, etc.)
AC (Complexité d'Attaque)
Attack Complexity
Low (L)
Peu de conditions requises pour exploiter
PR (Privilèges Requis)
Privileges Required
None (N)
Aucune authentification requise
UI (Interaction Utilisateur)
User Interaction
Unknown (P)
Interaction inconnue
S (Périmètre)
Scope
Unchanged (U)
Impact reste dans le périmètre du composant compromis
C (Impact Confidentialité)
Confidentiality Impact
High (H)
Divulgation totale d'informations
I (Impact Intégrité)
Integrity Impact
High (H)
Modification totale des données possible
A (Impact Disponibilité)
Availability Impact
High (H)
Interruption totale du service possible

> RÉSUMÉ DES IMPACTS

Confidentialité
High
Divulgation totale d'informations
Intégrité
High
Modification totale des données possible
Disponibilité
High
Interruption totale du service possible

> WEAKNESSES

CWE-807

> CWE DETAILED DESCRIPTIONS

CWE-807: Reliance on Untrusted Inputs in a Security Decision - The product uses a protection mechanism that relies on the existence or values of an input, but the input can be modified by an untrusted actor in a way that bypasses the protection mechanism.

> GITHUB SECURITY ADVISORY

GHSA-mmgp-wc2j-qcv7 HIGH

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

AFFECTED PACKAGES:
NPM / @anthropic-ai/claude-code
< 2.1.53
Fixed in: 2.1.53

> OSV (GOOGLE OPEN SOURCE VULNERABILITIES)

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

AFFECTED PACKAGES:
Unknown / Unknown
44 versions affected
ALIASES:
GHSA-mmgp-wc2j-qcv7

> HISTORIQUE DES MODIFICATIONS

Première apparition
20/03/2026 09:16
Source: NVD
đź“Š ENRICHISSEMENT 01/04/2026 06:02
CWE
Champ modifié: Description CWE
Ancienne valeur:
N/A
Nouvelle valeur:
CWE-807: Reliance on Untrusted Inputs in a Security Decision - The product uses a protection mechanism that relies on the existence or values of an input, but the input can be modified by an untrusted...
Total des modifications: 1 Dernière mise à jour: 7 months ago

> REFERENCES

https://github.com/anthropics/claude-code/security/advisories/GHSA-mmgp-wc2j-qcv...
« BACK_TO_HOME