AgentCorruption: A Stolen Execution Role Turns Memory into Persistent C2
- Autonomous Agents
- System Compromise & RCE
- Data Exfiltration
Zenity tested an AWS Bedrock AgentCore deployment, a managed environment for running AI agents, with a network-capable agent and a broad execution role. The agent relayed temporary role credentials from its metadata endpoint. Off-platform API calls then reached other memories and agents. The distinctive persistence path wrote short-term conversation events that configured extraction strategies could turn into long-term records; later retrieval directed the agent to a mutable command page. The reach was demonstrated within an account and region, not as a microVM escape or automatic cross-account compromise. The researchers observed major default-role restrictions on September 29; existing deployed roles still require independent inspection.
Mapped threat techniques
AML.T0080.000AI Agent Context Poisoning: MemoryAML.T0053AI Agent Tool InvocationAML.T0072Cyber Communication ChannelAML.T0025Exfiltration via Cyber Means