HighVulnerabilityLLM-specific

CVE-2026-18733: Amazon Strands Agents Tools prompt injection in shell tool

Source: NVD(opens in a new tab)
Identifier: CVE-2026-18733
Published: August 3, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.6%

Summary

Amazon Strands Agents Tools before 0.8.0 contains a prompt injection vulnerability in its shell tool. A crafted prompt that sets the non_interactive parameter to true bypasses the human consent gate, allowing remote actors to execute arbitrary operating system commands on the agent's host. The CNA, AMZN, rates it CVSS 4.0 7.5 (HIGH), and NVD has not yet provided an assessment.

Mitigation

To remediate this issue, users should upgrade to version 0.8.0.

Details

Scores and exploitation

CVSS score: 8.8(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack vector: network
Attack complexity: low
Privileges required: none
User interaction: required
EPSS: 0.6%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 4, 2026.
Disclosure date: August 3, 2026

Weaknesses and techniques

AI threat technique (MITRE ATLAS): AML.T0051

Classification

Attack type: Prompt injection
Attack sophistication: Trivial
AI component targeted: Agent
Impact: Confidentiality,
Integrity,
Availability
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-18733

First tracked: August 4, 2026 at 02:08 AM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 95% (self-assessed)

Topics

Prompt injection and jailbreaks

Summary

Mitigation

Topics

Related items