Prompt Injection in Amazon Strands Agents Tools <0.8.0 Allows Remote OS Cmd Exec
CVE-2026-18733 Published on August 3, 2026

Prompt injection bypasses shell tool consent gate in Strands Agents Tools
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.

Vendor Advisory NVD

Vulnerability Analysis

CVE-2026-18733 can be exploited with network access, requires user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to be very high.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
REQUIRED
Scope:
UNCHANGED
Confidentiality Impact:
HIGH
Integrity Impact:
HIGH
Availability Impact:
HIGH

Weakness Type

CWE-1427

Products Associated with CVE-2026-18733

stack.watch emails you whenever new vulnerabilities are published in Amazon Aws or Aws Strands Agents Tools. Just hit a watch button to start following.

Amazon Aws
 
Aws Strands Agents Tools
 

Affected Versions

AWS strands-agents-tools: