Theregister

Claude Cowork Vulnerable to File Exfiltration via Prompt Injection

First seen 15 Jan 2026, 23:02 UTC • News.Ycombinator

•83% similarity •43.9

Ask AI about this cluster

Article Content

Include sub-articles 1 / 1

Browse articles

ThreatCluster

Anthropic's Cowork productivity AI is vulnerable to file exfiltration attacks due to unresolved prompt injection issues. The vulnerability allows attackers to exploit isolation flaws in Claude's code execution environment, enabling sensitive file transmission to an attacker's account. This issue was first disclosed in October 2025 but remains unaddressed.

ThreatCluster AI

Attack Flow

12 entities, 16 inferred relationships (STIX 2.1).

Technique (3)

Data Breach
Prompt Injection
Sql Injection

Organization (3)

Anthropic
PromptArmor
Trend Micro

Affected Platform (4)

Chrome Extension
Cowork
Files API
SQLite MCP Server

Tool (2)

Claude
Curl

Relationships

Data Breach targets Chrome Extension
Data Breach targets Cowork
Data Breach targets Files API
Data Breach targets SQLite MCP Server
Prompt Injection targets Chrome Extension
Prompt Injection targets Cowork
Prompt Injection targets Files API
Prompt Injection targets SQLite MCP Server
Sql Injection targets Chrome Extension
Sql Injection targets Cowork
Sql Injection targets Files API
Sql Injection targets SQLite MCP Server
Claude related to Anthropic
Claude related to PromptArmor
Claude related to Trend Micro
Claude related to Curl

Community

Browse all →

Tracked Entities in This Story

Anthropic PromptArmor Trend Micro Chrome Extension Cowork Files API SQLite MCP Server Data Breach Prompt Injection Sql Injection Claude Curl

Claude Cowork Vulnerable to File Exfiltration via Prompt Injection

Ask AI about this cluster

Article Content

More articles in this cluster

Attack Flow

Defensive Countermeasures

Extracted Entities

Community

Continue Reading

Tracked Entities in This Story