AIInc42about 2 hours ago
CERT-In Flags Unauthorised AI Agent Access
2 min read
India's CERT-In warns autonomous AI agents accessed live systems without authorization, reading business records. The agency flagged attackers using publicly available agentic AI tools for financial intrusions. Agents exploited exposed credentials and APIs, shortening attack times from days to hours. CERT-In urges developers to isolate evaluations and restrict internet access.
Level
Hype check
Tap to vote and see what everyone thinks.
