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.
Fix
Vendor advisories in the News 1
- CVE-2026-18733 - Prompt injection bypasses shell tool consent gate in Strands Agents Tools AWS Security Bulletins · 2026-10-21
Every line above is quoted from NVD, CISA, Microsoft, the vendor's own advisory or DISA; nothing is generated.
Change history 1
- First seenCVSS 7.5NVD modified 2026-10-23 21:10
Affected (CPE criteria) 0
NVD has not attached CPE configurations yet.