Agents
An AWS agent exploited 33 of 37 new vulnerabilities in a test
AWS uses only new vulnerabilities, and the agent cannot get an exploit from the internet during the test.
Tag
AWS
79 stories carry this tag.
Security
6 AI agent frameworks operated a tool call from an attacker
The method, with the name Repeat-After-Me, tells a model to write again a text that is a tool call.
CSO OnlineClaimed, not confirmed
Security
AWS made Strands Box, an open source sandbox for AI agents
AWS writes that a rule can stop network traffic after the agent reads a file in a customer-data directory.
Agents
2 AWS engineers say hooks stop an AI agent with a fault
Hooks are deterministic Python code in the agent loop, and the engineers do not try to control the agent from the external side.
Security
One prompt could get access to all AgentCore agents in one AWS account
Zenity says that AWS removed the wide permissions. AWS says that access of an agent to its execution role credentials is expected.
CyberSecurityNewsClaimed, not confirmed
Security
One chat message gave Zenity control of all AgentCore agents
AWS made changes for part of the problem, and Zenity tells companies to give each agent a role with only the access it must have.
the-decoder.comClaimed, not confirmed
Security
The first AWS patch for AgentCore agents did not remove the risk
AWS corrected the default permissions of the agents between June 22 and September 29, Zenity wrote.
www.csoonline.comClaimed, not confirmed