AgentCorruption: A Stolen Execution Role Turns Memory into Persistent C2
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.
Why it relates: The extraction process can transform attacker-authored conversation text into longer-lived model context. The common boundary is data transformation integrity; no numerical feature engineering or training preprocessing is claimed.
Controlled broad-role AgentCore deployment with separate direct API and retained-memory/C2 branches; account/region scope, tool prerequisites and later default-role restrictions remain explicit.
AIA · Read the full case ↗ · SecureFlow · Read the full case ↗