CVE-2026-18733

Prompt injection bypasses shell tool consent gate in Strands Agents Tools

State: Published
Severity: 7.5 High
Published: Aug 3, 2026
Updated: Aug 4, 2026
Reserved: Aug 3, 2026

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.

Scores

CVSS	Score	Vector	Source
4.0	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	AMZN
3.1	8.8 High	CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H	AMZN

Weaknesses

CWE-1427 Improper neutralization of input used for LLM prompting

Affected Products

Product	Versions
strands-agents-toolsAWS	before 0.8.0Affected

References

https://pypi.org/project/strands-agents-tools/0.8.0/release-notespatch
https://aws.amazon.com/security/security-bulletins/2026-072-aws/vendor-advisory
https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8xrelease-notes

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.