Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
AWS strands-agents-tools
Exploitation
Public or AI PoC available; prioritize validation
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Amazon Strands Agents Tools是美国Amazon公司开源的一款人工智能智能体工具。 Amazon Strands Agents Tools 0.8.0之前版本存在提示词注入漏洞，该漏洞源于shell工具中的提示注入问题，可能导致远程攻击者通过特制提示将non_interactive参数设置为true，绕过人工同意门，在代理主机上执行任意操作系统命令。

CVSS 8.8 · High EPSS 0.57% · P45

Possible ATT&CK Techniques 1 AI

T1059.004 · Unix Shell

Affected Version Matrix 1

VendorProduct Version RangeStatus
AWS strands-agents-tools < 0.8.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-18733

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
Prompt injection bypasses shell tool consent gate in Strands Agents Tools
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
CWE-1427
Source: CVE Program / CVE List V5
Vulnerability Title
Amazon Strands Agents Tools 提示词注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
Amazon Strands Agents Tools是美国Amazon公司开源的一款人工智能智能体工具。 Amazon Strands Agents Tools 0.8.0之前版本存在提示词注入漏洞，该漏洞源于shell工具中的提示注入问题，可能导致远程攻击者通过特制提示将non_interactive参数设置为true，绕过人工同意门，在代理主机上执行任意操作系统命令。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
AWS strands-agents-tools 0 ~ 0.8.0 -

II. Public POCs for CVE-2026-18733

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 8570 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2026-18733

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-18733 (2)

Same Patch Batch · AWS · 2026-08-03 · 3 CVEs total

CVE-2026-18654 6.8 MEDIUM Disabled SSH host key verification in Amazon AWS CLI EMR helper commands
CVE-2026-18655 6.5 MEDIUM Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt I

IV. Related Vulnerabilities

Same product: strands-agents-tools
Same vendor: AWS
Same weakness: CWE-1427

V. Comments for CVE-2026-18733

No comments yet

Leave a comment