CVE-2026-79916

MaxKB is an open-source AI assistant for enterprise. Prior to 2.10.5-lts, authenticated workspace members can inject control characters into AWS Bedrock accesskeyid and secretaccesskey fields that updateawscredentials writes to /root/.aws/credentials without safe parsing. An attacker can append a...

CVE-2026-79916 MaxKB AWS Bedrock model credential injection leads to remote code execution

MaxKB is an open-source AI assistant for enterprise. Prior to 2.10.5-lts, authenticated workspace members can inject control characters into AWS Bedrock accesskeyid and secretaccesskey fields that updateawscredentials writes to /root/.aws/credentials without safe parsing. An attacker can append a...

CVE-2026-79916 MaxKB AWS Bedrock model credential injection leads to remote code execution

MaxKB is an open-source AI assistant for enterprise. Prior to 2.10.5-lts, authenticated workspace members can inject control characters into AWS Bedrock accesskeyid and secretaccesskey fields that updateawscredentials writes to /root/.aws/credentials without safe parsing. An attacker can append a...

CVE-2026-79916

MaxKB is an open-source enterprise AI assistant. Prior to 2.10.5-lts , authenticated workspace members can inject control characters into the AWS Bedrock access_key_id and secret_access_key fields. The _update_aws_credentials function writes these values to /root/.aws/credentials without safe par...

CVE-2026-79916 MaxKB AWS Bedrock model credential injection leads to remote code execution

MaxKB is an open-source AI assistant for enterprise. Prior to 2.10.5-lts, authenticated workspace members can inject control characters into AWS Bedrock accesskeyid and secretaccesskey fields that updateawscredentials writes to /root/.aws/credentials without safe parsing. An attacker can append a...

CVE-2026-79916: Improper Neutralization of Special Elements used in an OS Command

MaxKB is an open-source AI assistant for enterprise. Prior to 2.10.5-lts, authenticated workspace members can inject control characters into AWS Bedrock accesskeyid and secretaccesskey fields that updateawscredentials writes to /root/.aws/credentials without safe parsing. An attacker can append a...

PT-2026-96261

Name of the Vulnerable Software and Affected Versions MaxKB versions prior to 2.10.5-lts Description Authenticated workspace members can inject control characters into the AWS Bedrock access key id and secret access key fields. These values are processed by the update aws credentials function and...

PT-2026-82510

Name of the Vulnerable Software and Affected Versions GitLab AI Gateway versions 18.9.0 through 19.0.12 GitLab AI Gateway versions 19.1 through 19.1.7 GitLab AI Gateway versions 19.2 through 19.2.2 Description An issue in the AI Gateway component allows an authenticated user with Duo Agent Platfo...

GHSA-J6G5-3HH3-PGW8 AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK install_packages()

Summary The AWS Bedrock AgentCore Python SDK bedrock-agentcore provides tools for building AI agents, including a Code Interpreter client that installs Python packages into a managed sandbox. An issue exists where, under certain circumstances, improper neutralization of argument delimiters in the...

CVE-2026-16796: Improper Neutralization of Argument Delimiters in a Command

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

PT-2026-60522

AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform. Unintended logging of sensitive user content in the OpenTelemetry instrumentation in AWS Bedrock AgentCore Python SDK versions 1.4.8 and...

CVE-2026-15737: Insertion of Sensitive Information into Log File

AWS Bedrock AgentCore Python SDK is an open-source Python library that provides client tools for building AI agents on the Amazon Bedrock AgentCore platform. Unintended logging of sensitive user content in the OpenTelemetry instrumentation in AWS Bedrock AgentCore Python SDK versions 1.4.8 and...

CVE-2026-12530: Improper Neutralization of Argument Delimiters in a Command

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK versions = 1.1.3 and 1.6.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate thi...

PT-2026-50549

Name of the Vulnerable Software and Affected Versions AWS Bedrock AgentCore Python SDK versions 1.1.3 through 1.6.0 Description Improper neutralization of argument delimiters in the install packages method of the Code Interpreter client allows a remote authenticated user to execute arbitrary...

CVE-2026-42339 New API: SSRF Filter Bypass via 0.0.0.0

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 CVE-2025-59146 and hardened in v0.9.6 CVE-2025-62155 does not block the unspecified address 0.0.0.0. A regular...

CVE-2026-42339

CVE-2026-42339 (New API: SSRF Filter Bypass via 0.0.0.0) Affects New API (LLM gateway) up to v0.11.9-alpha.1. The SSRF protection is incomplete: 0.0.0.0/8 is not checked, allowing a regular user with a valid API token to request multimodal endpoints (/v1/chat/completions, /v1/responses, /v1/messa...

CVE-2026-42339: Server-Side Request Forgery (SSRF)

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. In versions 0.11.9-alpha.1 and prior, the SSRF protection introduced in v0.9.0.5 CVE-2025-59146 and hardened in v0.9.6 CVE-2025-62155 does not block the unspecified address 0.0.0.0. A regular...

AWS Bedrock Prompt Caching Support in Spring AI

In our previous blog post about Anthropic prompt caching, we explored how prompt caching dramatically reduces API costs and latency by reusing previously processed prompt content. We introduced Spring AI's five strategic caching patterns for Anthropic Claude models and showed how they automatical...

A Bootiful Podcast: AWS Developer Advocate and industry legend James Ward

Hi, Spring fans! In this installment I talk to AWS Developer Advocate and industry legend James Ward about AWS Bedrock, Amazon Cohere, Spring AI, MCP, and so much more!...

AWS VDP: Bedrock Guardrails Evasion with Prompt Formatting

Description Greetings, my name is ██████ and I am a Director here at NR Labs. We recently completed disclosure of this vulnerability by working with ████ and the AWS Security team. We are submitting this issue to the AWS VDP to create an official record of the issue with AWS in preparation for a...