AccountSubscribe

AI agents find $4.6M in blockchain smart contract exploits

Anthropic Frontier Red Team (community feed)December 1, 2025Vulnerabilities AI AppSec

We evaluated AI agents' ability to exploit smart contracts using a new benchmark comprising contracts that were actually exploited.

Summary from Anthropic Frontier Red Team (community feed).

Read the full article at Anthropic Frontier Red Team (community feed)

Explained

The technology and terms in this story. Learn more

TechnologyAI agentAn AI model that acts on its own: it plans steps, uses tools and takes actions, not just answers.
ConceptExploitCode or a technique that turns a software flaw into something an attacker can actually use.

More in Vulnerabilities

Smart TVs can harbor unpatched security flaws and track what you watch

Help Net Securityjust nowVulnerabilities

SANS Stormcast Friday, October 30th, 2026: Local Ghidra Server for Malware Analysis Labs; Claude Finds Linux Kernel Multipath TCP RCE (CVE-2026-98432); Hugging Face Cryptomining Malware Campaign

Podcast8 minSANS Internet Storm Center StormCast2h agoVulnerabilitiesAIEndpointCVE-2026-98432

Billions stolen in Binance hack

Podcast10 minRisky Business News3h agoVulnerabilitiesThreat IntelNetwork

Researchers find bugs in 5 AI developer tools, with OpenAI and Microsoft flaws still unpatched

The Register Security6h agoVulnerabilitiesAI

Cisco security advisory (AV26-1102) - Update 1

Canadian Centre for Cyber Security9h agoVulnerabilitiesNetwork

AI agents find $4.6M in blockchain smart contract exploits | SecurityTabs