🧰 AWS Bedrock

The items that name it 33

• Northflank security breach leads to abuse of customers' AI API keys
  articleas classification.technologies2026-10-31
• “Black October” for AI Developer Platforms
  writeupas classification.technologies2026-10-30
• LiteLLM Compromised in Fresh Supply Chain Attack
  articleas classification.technologies2026-10-23
• Datadog pathrunner: AWS IAM privilege escalation framework
  toolas classification.technologies2026-10-20
• [tl;dr sec] #350 - Reverse Engineer Anything, Tracking AI-integrated Malware, Test-driving Jev
  articleas classification.technologies2026-10-15
• AgentCorruption: How A Single Prompt Collapsed The Entire Cloud Security Model
  writeupas classification.technologies2026-10-08
• Anthropic Introduces 3-Tier Cyber Verification Program for AI Access
  articleas classification.technologies2026-10-07
• Kubernetes Agent Sandbox on AWS EKS (Step-by-Step Guide)
  writeupas classification.technologies2026-10-07
• Identity-aware AI data agents with AWS Lake Formation and Trusted Identity Propagation
  articleas classification.technologies2026-10-06
• Expanding the Cyber Verification Program
  articleas classification.technologies2026-10-06
• Beyond valid credentials: How exposed AWS keys are tested for Amazon Bedrock access
  writeupas classification.technologies2026-10-06
• ICYMI: August 2026 @AWS Security
  articleas classification.technologies2026-09-23
• Transforming Bedrock Guardrails events into OCSF with CloudWatch
  writeupas affected products2026-09-21

  Generative AI service with Guardrails feature; model invocation logging used to capture guardrail trace data for transformation into OCSF

• Attacker infrastructure, but vibe-coded: tracking the evolution of credential harvesting platforms
  writeupas classification.technologies2026-09-18
• Run open weight models on Amazon Bedrock in AWS European Sovereign Cloud
  articleas classification.technologies2026-09-17
• Building an AI Detection Engine That Understands Agent Intent
  articleas classification.technologies2026-09-17
• Operationalizing least privilege: Automate IAM remediation through your CI/CD pipeline
  writeupas classification.technologies2026-09-15
• Off Guard: Breaking LiteLLM from authentication bypass to cloud compromise
  writeupas classification.technologies2026-09-09
• Incident response guide for AWS CloudTrail investigations – Part 2 | Amazon Web Services
  writeupas classification.technologies2026-09-03
• agentgg
  repoas classification.technologies2026-08-23
• Orca Security: AI Agents Security
  articleas classification.technologies2026-08-14
• Orca Security: Shadow AI Governance
  articleas classification.technologies2026-08-13
• Orca Security: AI-BOM
  articleas classification.technologies2026-07-31
• AI-Powered Threat Modeling
  repoas tools2026-07-17

  Cloud LLM provider option for AITM (default provider; example uses claude-sonnet-4)

• promptfoo
  repoas classification.technologies2026-07-14
• NVIDIA/garak
  repoas classification.technologies2026-07-14
• apisec-inc/AI-Surface
  repoas affected products2026-07-11It is written here as AWS Bedrock (us.anthropic.claude-sonnet-4, src/support_workflow.py).

  demo app LLM SDK call site

• Defending Code Reference Harness
  repoas classification.technologies2026-06-05
• Metis
  repoas tools2026-05-31

  Supported LLM provider for Metis

• garak v0.17.0 — adds EU AI Act risk-category mapping
  repoas affected products

  suppressed_params support and reasoning model support added (v0.16.0/v0.15.0)

• AWS, Google, and Vercel Agent Flaws Let Attackers Trigger Tools Without Running the Model
  articleas classification.technologies
• CVE-2026-18655: Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server (awslabs
  advisoryas classification.technologies
• Sockpuppeting: How a Single Line Can Bypass LLM Safety Guardrails | TrendAI (US)
  writeupas affected products

  Blocks assistant-role final messages at API layer, preventing sockpuppeting

In every workspace you can read 34