Posts tagged “ai-security”

• MCP TypeScript SDK 2.3.1: Enable Legacy Token Audience Checks

  Configure token audience checks in MCP TypeScript SDK 2.3.1 legacy bearer auth: verifier mapping, URL matching rules and staging checks before rollout.

• Security-One 27B: When to Use It for Agent Security Triage

  Evaluate Security-One 27B for agent security triage: reported detection tradeoffs, API pricing, self-hosting requirements and a review-only pilot plan.

• OpenAI Reports Hidden-Reasoning Extraction: What Agent Builders Should Protect

  OpenAI’s reasoning-extraction disclosure puts agent transcripts, replay controls and streaming review under scrutiny. What builders should protect.

• Anthropic’s AI Misuse Report Makes Model Provenance a Supply-Chain Problem

  Anthropic’s September report shows why model identity, transcript custody, agent traces, and account revocation now belong in one security review.

← Back to blog