CVE-2026-18733: A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors
highvulnerability
security
Summary
A prompt injection vulnerability (tricking an AI by hiding instructions in its input) in the shell tool of Amazon Strands Agents Tools before version 0.8.0 allows attackers to run arbitrary operating system commands on the agent's host computer by crafting a prompt that sets the non_interactive parameter to true, which bypasses the requirement for human approval.
Solution / Mitigation
Users should upgrade to version 0.8.0 of Amazon Strands Agents Tools.
Vulnerability Details
CVSS Score
8.8(high)
EPSS (30-day exploit probability)
EPSS: 0.0%
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
Disclosure Date
August 3, 2026
Classification
Attack Type
Prompt Injection
Attack SophisticationModerate
Impact (CIA+S)
integrityavailability
Taxonomy References
MITRE ATLAS (AI/ML Threat Technique)
Affected Vendors
Amazon
Related Issues
Monthly digest — independent AI security research
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-18733
First tracked: August 4, 2026 at 02:08 AM
Classified by LLM (prompt v3) · confidence: 92%