CVE-2026-18733Network attack vector

Host command execution via LLM-controlled consent bypass

Published Aug 3, 2026 · Updated Aug 3, 2026

Prompt injection in the shell tool in Amazon Strands Agents Tools before 0.8.0 allows remote attackers to execute host commands. The LLM-controllable non_interactive input is honored as true, causing the tool to skip its human consent gate before running a generated command. Exploitation requires an enabled shell tool and crafted content that the agent processes; commands run with the agent process's privileges.

CVSS severity7.5
High
EPSS probability0.32%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Prompt injection in the shell tool in Amazon Strands Agents Tools before 0.8.0 allows remote attackers to execute host commands. The LLM-controllable non_interactive input is honored as true, causing the tool to skip its human consent gate before running a generated command. Exploitation requires an enabled shell tool and crafted content that the agent processes; commands run with the agent process's privileges.

The record

CVE
CVE-2026-18733
Published
Aug 3, 2026
Updated
Aug 3, 2026
Vendor
Amazon Web Services
Product
Strands Agents Tools
Classifications
CWE-1427, T1059
Attack vector
network
Privileges
unauthenticated

Timeline

How it unfolded

  1. Aug 3, 2026CVE publishedPublication date reported by the CVE source.
  2. Aug 3, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=0 <0.8.0

What conditions does exploitation require?

Attack vectornetwork
Required privilegesunauthenticated

What is affected?

Amazon Web Services · Strands Agents Toolsversion=0 <0.8.0

Published CVSS scores

8.8Amazon Web ServicesCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
7.5Amazon Web ServicesCVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesunauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-1427Improper Neutralization of Input Used for LLM Prompting
T1059Command and Scripting Interpreter

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo