ZombAIs: From Prompt Injection to C2 with Claude Computer Use
mediumnewsLLM-Specific
securitysafety
Source: Embrace The RedOctober 24, 2024
Summary
Claude Computer Use is a new AI tool from Anthropic that lets Claude take screenshots and run commands on computers autonomously. The feature carries serious security risks because of prompt injection (tricking an AI by hiding malicious instructions in its input), which could allow attackers to make Claude execute unwanted commands on machines it controls.
Classification
Attack Type
Prompt Injection
Attack SophisticationModerate
Impact (CIA+S)
integrityavailability
Affected Vendors
Anthropic
Related Issues
Original source: https://embracethered.com/blog/posts/2024/claude-computer-use-c2-the-zombais-are-coming/
First tracked: February 12, 2026 at 02:20 PM
Classified by LLM (prompt v3) · confidence: 85%