Rewindex/CVEs/Amazon Web Services

CVE-2026-18733: Prompt injection bypasses shell tool consent gate in Strands Agents Tools

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.

Vector CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H · CWE-1427

Tracked companies

Amazon Web Services

Mapped from the CVE’s affected-product data, NVD CPE matches, vendor advisories or package feeds. A mapping means the vendor’s software is named, not that its hosted service was exposed.

Status incidents that name it

No tracked status incident names this CVE.

Affected vendors and products

AWS: strands-agents-tools

References

• CVE record on cve.org (opens in new tab)
• NVD entry (opens in new tab)
• aws.amazon.com/security/security-bulletins/2026-072-aws/ (opens in new tab)
• github.com/strands-agents/tools/security/advisories/GHSA-mqvc-p852-wf8x (opens in new tab)
• pypi.org/project/strands-agents-tools/0.8.0/ (opens in new tab)

All CVEsMarkdownJSON

• CVE records from the CVE Program (cve.org). CVE® is a registered trademark of The MITRE Corporation. (opens in new tab)
• This product uses data from the NVD API but is not endorsed or certified by the NVD. (opens in new tab)
• Known Exploited Vulnerabilities catalog from CISA. (opens in new tab)
• EPSS scores from FIRST (Exploit Prediction Scoring System). (opens in new tab)