CVE-2026-18733
8.8
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Summary
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.
Affected Software
| Vendor | Product | Version Range | Status |
|---|---|---|---|
| AWS | strands-agents-tools | 0 < 0.8.0 | affected |
Weaknesses
- CWE-1427: CWE-1427 Improper neutralization of input used for LLM prompting
References
- https://pypi.org/project/strands-agents-tools/0.8.0/
- https://aws.amazon.com/security/security-bulletins/2026-072-aws/
- https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x
Feedback
Was this page helpful?
Glad to hear it! Please tell us how we can improve.
Sorry to hear that. Please tell us how we can improve.