CVE-2026-18733: Prompt injection bypasses shell tool consent gate in Strands Agents Tools
Affects strands-agents-toolsSource AWS Security Bulletins
Not known to be exploited · CVSS 8.8 High : upgrade to 0.8.0 soon.
Data as of 5 Nov 2026, 00:01 UTC
- EPSS
- 0.5% chance of exploitation in 30 days – higher than 47% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
- Patch
- Available – fixed in 0.8.0
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:HExploitation evidence
Disclosed: evidence found.
CVE published 3 Aug 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors
A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 5 Nov 2026.
What to do
Upgrade strands-agents-tools to 0.8.0.
Affected software
| Product | Affected | Fixed in |
|---|---|---|
npmstrands-agents-toolspkg:npm/strands-agents-toolsOther threats | Affected
| Fixed in
|
Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.
AI-suggested
A fix is available in strands-agents-tools version 0.8.0. Users should upgrade to this version or later. Until upgrading, do not expose the shell tool to agents processing untrusted content, and run agents using the shell tool in isolated, least-privilege environments to contain potential command execution.
Description
Bulletin ID: 2026-072-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/03/2026 13:30 PM PDT Description: Strands Agents is an open-source SDK for building AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the shell tool for executing operating system commands on the agent's host. We identified CVE-2026-18733. The shell tool includes a human consent gate that prompts the operator to approve commands before they run. The tool also exposed a non_interactive parameter in the input schema that the large language model (LLM) could control. A crafted prompt, for example one delivered through untrusted content the agent reads (indirect prompt injection), could set non_interactive to true, which bypasses the consent gate and allows arbitrary operating system commands to execute on the agent's host without operator approval. Impacted versions: < 0.8.0 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.