2026-01-21 · 2026-Q1

Claude Code API Key Exfiltration

Primary layerL5 ConfigSecondary:L1 Credential L8 Output / Destination

Who wrote the file that runs on open?
The question layer 5 asks, and failed here.

Fixable: Vendor patch
Vendor response: Patched
In the wild: No
Actor: Attacker

Target

Anthropic Claude Code

Impact

Malicious settings file redirects API requests to attacker endpoint before trust prompt; stolen API key grants access to team's shared resources

Root cause

API requests issued before trust confirmation prompt

CVE

CVE-2026-21852

Sources

Catalog

View this entry in the catalog

Cite this: AgentProv incident record: Claude Code API Key Exfiltration (2026-01-21). https://agentprov.com/incidents/2026-01-21-claude-code-api-key-exfiltration

Also L5 · 2026-10-25Planted AGENTS.md in a Downloads Folder Got Codex to Install Malware; a CLAUDE.md Variant Exposed Claude Code's OAuth TokenL5Config
Also L5 · 2026-10-21MCP Inspector Advisory Batch: Two Critical Paths From Connecting to a Malicious MCP Server to Local Command ExecutionL5Config
Also L5 · 2026-10-16Claude Agent SDK: A Crafted Session ID Injects an MCP Server and Runs Commands Past SDK Permissions (CVE-2026-96620)L5Config