CVE-2026-18830

8.1 HIGH

Published 2026-08-04 · Updated 2026-08-06

AI risk analysis

Summary: This flaw allows an authenticated user to bypass security controls by crafting specific content in conversation messages, potentially executing unauthorized tools.
Exploitability: Exploitation requires authentication and knowledge of the crafted content, making it moderately difficult.
Blast radius: If exploited, the impact is limited to the execution of unauthorized tools within the affected system, potentially leading to data exposure or misuse.
Detection: No reliable host or network indicator is derivable from the published description.
Prioritized remediation: Upgrade to the latest version of Amazon Bedrock AgentCore as addressed by AWS.

auth-bypassrcewebaws

Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.

NVD description

Insufficient input validation in Amazon Bedrock AgentCore harness might allow an authenticated remote user to execute configured tools bypassing model invocation and security controls via crafted content blocks in conversation messages. AWS has addressed this issue. No customer action is required.

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:N

Weaknesses

CWE-1287

References

https://aws.amazon.com/security/security-bulletins/2026-073-aws/

Data: NVD (public domain). Analysis: local $0 model. Defensive use only.