As cited
Copy frozen at (site build).
Inside 90 days of attacks on AI infrastructure
No summary had been written when this copy was frozen.
- First seen by Cybersecurity Tracker
Source attribution
Correction
Correction recorded as of .
ai security
Inside 90 days of attacks on AI infrastructure
Wiz security researchers deployed honeypots to monitor attacks on artificial intelligence (AI) infrastructure and discovered active campaigns targeting LiteLLM, Model Context Protocol (MCP) servers, and AI frameworks. Attackers exploited remote code execution (RCE) vulnerabilities, blind prompt injection techniques, and memory-based credential theft to compromise these systems.
Why it matters: Organizations running LiteLLM, MCP servers, or AI frameworks need to assess their exposure to RCE and prompt injection attacks, implement strict input validation, and audit credential handling in memory to prevent unauthorized access.
- Source published
- First seen by Cybersecurity Tracker