Which versions of Strands Agents Tools are affected by EUVD-2026-52432?

Amazon Strands Agents Tools versions below 0.8.0 contain a prompt injection vulnerability enabling unauthenticated remote code execution on agent infrastructure through malicious inputs that bypass…. A patch is available.

How to fix or mitigate EUVD-2026-52432?

Within 24 hours, conduct a complete inventory of Amazon Strands Agents Tools deployments across your environment and identify all systems running versions prior to 0.8.0, with priority flagging for instances with shell tool functionality enabled. Within 7 days, upgrade all affected systems to version 0.8.0 or later through the vendor patch release; if immediate patching is operationally infeasible, disable shell tools entirely as a mandatory interim control. Within 30 days, confirm patch deployment across all systems, audit system logs and agent execution records for suspicious prompt patterns or unauthorized command execution that may have occurred during the vulnerability exposure period, and establish ongoing monitoring for injection attempts.

Strands Agents Tools EUVD-2026-52432

Q: What is the CVSS score of EUVD-2026-52432?

EUVD-2026-52432 has a CVSS 4.0 base score of 7.5 (High). CVSS 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X. EPSS exploitation probability: 0.3%.

| CVE-2026-18733 HIGH

Improper Neutralization of Input Used for LLM Prompting (CWE-1427)

2026-08-03 AMZN

Authentication Bypass Strands Agents Tools

7.5

CVSS 4.0 · Vendor: AMZN

Severity by source

Vendor (AMZN) PRIMARY

7.5 HIGH

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

vuln.today AI

8.3 HIGH

Shell tool must be enabled and processing untrusted input (AC:H); scope changes from agent context to host OS (S:C); no attacker credentials required (PR:N).

3.1 AV:N/AC:H/PR:N/UI:R/S:C/C:H/I:H/A:H

4.0 AV:N/AC:L/AT:P/PR:N/UI:A/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Primary rating from Vendor (AMZN).

CVSS VectorVendor: AMZN

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Attack Vector

Network

Attack Complexity

Low

Privileges Required

None

User Interaction

Scope

Lifecycle Timeline

Analysis Updated

Aug 03, 2026 - 21:30 vuln.today

v2 (cvss_changed)

Re-analysis Queued

Aug 03, 2026 - 21:22 vuln.today

cvss_changed

CVSS changed

Aug 03, 2026 - 21:22 NVD

8.8 (HIGH) 7.5 (HIGH)

Analysis Generated

Aug 03, 2026 - 21:07 vuln.today

CVE Published

Aug 03, 2026 - 20:33 cve.org

HIGH 8.8

DescriptionCVE.org

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.

AnalysisAI

Prompt injection in Amazon Strands Agents Tools before 0.8.0 enables remote actors to execute arbitrary OS commands on the agent's host by crafting input that sets the shell tool's non_interactive parameter to true, silencing the human consent gate designed to require approval before running shell commands. The CVSS 4.0 vector (AV:N/PR:N) confirms no attacker authentication is required, though the agent must actively process the malicious prompt (UI:A) and the shell tool must be in use (AT:P). …

Unlock full vulnerability intelligence

Risk assessment & exploitation conditions
Attack chain visualization
Remediation with exact patch versions
Threat intelligence from 22 sources
Personal watchlist & email alerts

Continue with Google Continue with GitHub

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access

technique details hidden

Delivery

technique details hidden

Exploit

technique details hidden

Execution

technique details hidden

Persist

technique details hidden

Impact

technique details hidden

Access

technique details hidden

Delivery

technique details hidden

Exploit

technique details hidden

Execution

technique details hidden

Persist

technique details hidden

Impact

technique details hidden

Vulnerability AssessmentAI

Exploitation	The Strands shell tool must be enabled in the agent's tool configuration - agents that do not register or use the shell tool are entirely unaffected. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment	The CVSS 4.0 score of 7.5 reflects high impact across confidentiality, integrity, and availability on the vulnerable system (VC:H/VI:H/VA:H), with no impact on subsequent systems (SC:N/SI:N/SA:N). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario	Full exploit scenario with step-by-step reproduction available after sign-in.
Remediation	The primary fix is to upgrade strands-agents-tools to version 0.8.0 or later via pip (`pip install strands-agents-tools>=0.8.0`), available at https://pypi.org/project/strands-agents-tools/0.8.0/ and confirmed by the AWS advisory at https://aws.amazon.com/security/security-bulletins/2026-072-aws/. … Detailed patch versions, workarounds, and compensating controls in full report.

Recommended ActionAI

Within 24 hours, conduct a complete inventory of Amazon Strands Agents Tools deployments across your environment and identify all systems running versions prior to 0.8.0, with priority flagging for instances with shell tool functionality enabled. …

Threat intelligence, references, and detailed analysis are available after sign-in.