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 craft…
高危 CVSS 8.8
摘要
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.
中文摘要建设中，暂以英文摘要呈现（DR-003 v2）。
深度研判 · 自动通道
该漏洞尚未生成深度研判报告（DR-003 v2 AI pipeline 建设中）。
Lint 边界警告 (2)
以下是本次研判 lint 阶段发现的非阻塞性警告（如引用 URL 未在白名单内）。这些不影响漏洞条目可用性，仅为透明度披露（参 DR-002）。
-
REF_URL_NOT_ALLOWLISTEDurl not in allowlist: https://aws.amazon.com/security/security-bulletins/2026-072-aws/ -
REF_URL_NOT_ALLOWLISTEDurl not in allowlist: https://pypi.org/project/strands-agents-tools/0.8.0/
数据来源
- NVD DATABASE
原始链接
- https://aws.amazon.com/security/security-bulletins/2026-072-aws/
- https://github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x
- https://pypi.org/project/strands-agents-tools/0.8.0/
时间线
- nvd_ingest NVD