High severity · published Aug 3, 2026
CVE-2026-18733
Prompt injection bypasses shell tool consent gate in Strands Agents Tools
8.8
CVSS
0.6%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
Required
Confidentiality
High
Integrity
High
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 47% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
ST
strands-agents-tools · AWS
before 0.8.0 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-18733
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-18733
aws.amazon.com
https://aws.amazon.com/security/security-bulletins/2026-072-aws/
github.com
https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x
pypi.org
https://pypi.org/project/strands-agents-tools/0.8.0/
More from strands-agents-tools
8.1
CVE-2026-19111
Insecure direct object reference in Strands Agents Tools memory tool namespace isolation
7.4
CVE-2026-18394
Incorrect authorization in Strands Agents Tools http_request proxy credential exfiltration