Back to vendor advisories
AWS Security BulletinsCVE-2026-18733

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

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.

Not listedCVSS not listedNot listed severity
Scope

What the vendor says is affected

The collected bulletin did not provide a separate affected-products list. Check the original bulletin before making an exposure decision.

Update history

What changed in later vendor updates

SecurityAlert records field-level changes from the point we begin following a bulletin. Earlier vendor changes may not have a field-by-field record.

    • The vendor changed the advisory's last-updated date.
    • The vendor changed the advisory's last-updated date.
    • The vendor changed the advisory's last-updated date.
Timeline

When this advisory changed

  1. Added to SecurityAlert

    We collected the advisory from the official source.

  2. Published by AWS

    The publication date reported by the vendor.

  3. Confirmed at the source

    Our collector saw this advisory during a later source check.

Vulnerabilities

CVEs named in this advisory