What’s Vulnerable › Vulnerabilities

CVE-2026-18733: Prompt injection bypasses shell tool consent gate in Strands Agents Tools

• Severity: high (CVSS 8.8 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.6% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-08-03 · updated 2026-10-23
• Weakness: CWE-1427

Description

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.

Affected products

• AWS strands-agents-tools: before 0.8.0 — fixed in 0.8.0

How to fix

Upgrade to a fixed version: AWS strands-agents-tools 0.8.0. Check the vendor advisory for mitigations.

References

• https://aws.amazon.com/security/security-bulletins/2026-072-aws/
• https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x
• https://pypi.org/project/strands-agents-tools/0.8.0/

Get alerted when CVE-2026-18733 or the next vulnerability affects your stack