A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate.
To remediate this issue, users should upgrade to version 0.8.0.
References
Configurations
No configuration.
History
No history.
Information
Published : 2026-08-03 21:16
Updated : 2026-08-04 20:16
NVD link : CVE-2026-18733
Mitre link : CVE-2026-18733
CVE.ORG link : CVE-2026-18733
JSON object : View
Products Affected
No product.
CWE
No CWE.
