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.
Published: 2026-08-03
Score: 7.5 High
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

No analysis available yet.

Remediation

No remediation available yet.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Mon, 03 Aug 2026 20:45:00 +0000

Type Values Removed Values Added
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.
Title Prompt injection bypasses shell tool consent gate in Strands Agents Tools
First Time appeared Aws
Aws strands-agents-tools
Weaknesses CWE-1427
CPEs cpe:2.3:a:aws:strands-agents-tools:*:*:*:*:*:*:*:*
Vendors & Products Aws
Aws strands-agents-tools
References
Metrics cvssV3_1

{'score': 8.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 7.5, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N'}

Subscriptions

Aws Strands-agents-tools
cve-icon MITRE

Status: PUBLISHED

Assigner: AMZN

Published:

Updated: 2026-08-03T20:35:23.023Z

Reserved: 2026-08-03T18:48:48.218Z

Link: CVE-2026-18733

cve-icon Vulnrichment

No data.

cve-icon NVD

No data.

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses
  • CWE-1427

    Improper Neutralization of Input Used for LLM Prompting