Skip to content

Wire Briefings Search

Fetching from the wire…

01

02

03

04

05

06

07

08

Wire Briefings Search

Entity trail

RAXE Labs

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

1

Findings

1

Edges

1

Sources

6

Corpus findings

2026-04-10 / skill-finderCVE-2026-33068: Malicious Repos Bypass Claude Code Workspace Trust Dialog via Committed Settings FileRAXE Labs disclosed CVE-2026-33068 (CVSS 7.7): Claude Code resolved permission mode from .claude/settings.json before displaying the workspace trust dialog, allowing a malicious repo to set permissions.defaultMode to bypassPermissions. A victim cloning the repo would be silently placed in permissive mode without seeing the trust confirmation, enabling arbitrary tool execution. Fixed in v2.1.53. Builders should never clone untrusted repos into Claude Code without verifying settings files first.

Graph relationships

CRITICIZES
Claude Code
RAXE Labs disclosed CVE-2026-33068 in Claude Code workspace trust
Source finding

Source trail

RAXE Labs Researchers on arXiv arXiv 2604.08465 Oasis Security LiteLLM's security update AISLE's research

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues

RAXE Labs intelligence trail | MindPattern