CVE-2026-18394: CWE-863: Incorrect Authorization in AWS Strands Agents Tools
Bulletin ID: 2026-069-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 07/31/2026 12:30 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 http_request tool for making HTTP API requests. We identified CVE-2026-18394, an incorrect authorization issue in the http_request tool. Operators can use the HTTP_REQUEST_TOKEN_CONFIG allowlist to bind a credential to a set of approved hostnames so it is sent only to those hosts. The tool also exposed a proxies parameter in the input schema that the large language model (LLM) could control. A crafted prompt, for example one delivered through untrusted web content the agent reads (indirect prompt injection), could set proxies to an actor-controlled endpoint. The hostname allowlist check still passes on the request URL, the credential is attached, and the request is routed through the actor's proxy on the first hop, disclosing the credential in cleartext in the Authorization header. Impacted versions: < 0.8.2 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.
AI Analysis
Technical Summary
The vulnerability CVE-2026-18394 affects the http_request tool in the strands-agents-tools package, part of the AWS Strands Agents open-source SDK. The tool uses an HTTP_REQUEST_TOKEN_CONFIG allowlist to restrict credentials to approved hostnames. However, the proxies parameter exposed in the input schema can be controlled by the large language model (LLM). An attacker can craft a prompt that sets the proxies parameter to an attacker-controlled endpoint. Although the hostname allowlist check passes on the request URL, the credential is attached and the request is routed through the malicious proxy on the first hop, exposing the credential in cleartext in the Authorization header. This is an incorrect authorization issue classified under CWE-863. The vulnerability affects versions before 0.8.2. AWS provides a security bulletin with further details and manages remediation for this cloud service.
Potential Impact
An attacker able to influence the input prompt can cause the http_request tool to send credentials through a malicious proxy, exposing sensitive authorization tokens in cleartext. This can lead to credential disclosure and potential misuse of those credentials. The vulnerability does not directly allow code execution or availability impact but compromises confidentiality of credentials.
Mitigation Recommendations
AWS manages remediation for this cloud-hosted service. A fix is available in versions 0.8.2 and later. Users should upgrade to version 0.8.2 or later as per the AWS security bulletin. Review the official AWS advisory at https://aws.amazon.com/security/security-bulletins/2026-069-aws/ for the latest remediation guidance.
CVE-2026-18394: CWE-863: Incorrect Authorization in AWS Strands Agents Tools
Description
Bulletin ID: 2026-069-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 07/31/2026 12:30 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 http_request tool for making HTTP API requests. We identified CVE-2026-18394, an incorrect authorization issue in the http_request tool. Operators can use the HTTP_REQUEST_TOKEN_CONFIG allowlist to bind a credential to a set of approved hostnames so it is sent only to those hosts. The tool also exposed a proxies parameter in the input schema that the large language model (LLM) could control. A crafted prompt, for example one delivered through untrusted web content the agent reads (indirect prompt injection), could set proxies to an actor-controlled endpoint. The hostname allowlist check still passes on the request URL, the credential is attached, and the request is routed through the actor's proxy on the first hop, disclosing the credential in cleartext in the Authorization header. Impacted versions: < 0.8.2 Please refer to the article below for the most up-to-date and complete information related to this AWS Security Bulletin.
CVSS v3.1
Score 7.4high
Affected software
AWS
Strands Agents Tools
pkg:github/strands-agents/toolsRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability CVE-2026-18394 affects the http_request tool in the strands-agents-tools package, part of the AWS Strands Agents open-source SDK. The tool uses an HTTP_REQUEST_TOKEN_CONFIG allowlist to restrict credentials to approved hostnames. However, the proxies parameter exposed in the input schema can be controlled by the large language model (LLM). An attacker can craft a prompt that sets the proxies parameter to an attacker-controlled endpoint. Although the hostname allowlist check passes on the request URL, the credential is attached and the request is routed through the malicious proxy on the first hop, exposing the credential in cleartext in the Authorization header. This is an incorrect authorization issue classified under CWE-863. The vulnerability affects versions before 0.8.2. AWS provides a security bulletin with further details and manages remediation for this cloud service.
Potential Impact
An attacker able to influence the input prompt can cause the http_request tool to send credentials through a malicious proxy, exposing sensitive authorization tokens in cleartext. This can lead to credential disclosure and potential misuse of those credentials. The vulnerability does not directly allow code execution or availability impact but compromises confidentiality of credentials.
Mitigation Recommendations
AWS manages remediation for this cloud-hosted service. A fix is available in versions 0.8.2 and later. Users should upgrade to version 0.8.2 or later as per the AWS security bulletin. Review the official AWS advisory at https://aws.amazon.com/security/security-bulletins/2026-069-aws/ for the latest remediation guidance.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- AMZN
- Date Reserved
- 2026-07-30T14:47:05.047Z
- Cvss Version
- 3.1
- State
- PUBLISHED
- Is Cloud Service
- true
- Vendor Advisory Urls
- [{"url":"https://aws.amazon.com/security/security-bulletins/2026-069-aws/","vendor":"AWS"}]
Threat ID: 6a6cfc17bf32cb7a3432689c
Added to database: 07/31/2026, 19:48:39 UTC
Last enriched: 08/15/2026, 18:31:20 UTC
Last updated: 09/14/2026, 22:01:32 UTC
Views: 147
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.