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 228d 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