PulseAugur
EN
LIVE 08:30:57

Claude Code vulnerability exposed API keys before trust prompt

By PulseAugur Editorial · [1 sources] ·

A security vulnerability, tracked as CVE-2026-21852, has been identified in Claude Code versions prior to 2.0.65. The flaw allowed malicious repositories to exfiltrate API keys by setting a specific configuration value before the user was prompted to confirm trust in the repository. This means simply opening a compromised folder could lead to an API key being sent to an attacker-controlled server without any further user interaction. The issue has been fixed in version 2.0.65 and later. AI

IMPACT Exposes a critical security flaw in AI coding assistants, highlighting the need for robust trust mechanisms before executing user-provided code configurations.

RANK_REASON Disclosure of a security vulnerability and its fix in a specific software tool.

Read on dev.to — Claude Code tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Claude Code vulnerability exposed API keys before trust prompt

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Disclosure of a security vulnerability and its fix in a specific software tool.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
safety, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
47 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — Claude Code tag TIER_1 English(EN) · Ramdai Bista ·

    Claude Code Sent Your API Key to an Attacker's Server Before It Asked If You Trusted the Repo

    <p>Claude Code's workspace trust prompt exists to stop an untrusted repository's config from doing anything before you've confirmed you trust it. For versions below 2.0.65, one config value got processed before that prompt ever appeared — and it was the one that controls where yo…

RELATED ENTITIES

RELATED TOPICS