Theregister Claude Cowork Vulnerable to File Exfiltration via Prompt Injection
Article Content
Browse articles 
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.
Ask AI about this cluster
Answers cite the sources they use
Updated 229d ago How this analysis works
More articles in this cluster (3)
Following this threat?
Track Anthropic in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.
Free account · no card needed
Continue Reading
PHP2Shell Vulnerabilities Exploited by AI-Driven Attackers Threat actors have exploited PHP2Shell vulnerabilities (CVE-2026-109618 and CVE-2026-109619) to target a government entity in Europe, gaining access to sensitive data within two hours of the initial breach. The attackers utilized AI tools for reconnaissance and post-exploitation activities, including accessing… 
Lazarus APT Launches Operation FlashHole Using AI and Post-Quantum Cryptography Kaspersky has identified a cyberespionage campaign, dubbed Operation FlashHole, attributed to the Lazarus APT group, active since July 2025. The campaign has targeted at least three organizations in South Korea's construction, software, and wire-communication sectors. Attack methods include spear-phishing emails…