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…
High CVSS 8.8
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.
In-depth triage · Auto channel
No in-depth report has been generated yet (DR-003 v2 AI pipeline is under construction).
Lint boundary warnings (2)
The following non-blocking warnings were raised during the lint phase of this triage (e.g. reference URLs not yet on the allowlist). They do not affect entry usability and are disclosed for transparency (see 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/
Sources
- NVD DATABASE
Original Links
- 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/
Timeline
- nvd_ingest NVD