NewsMicrosoft AI Toolkit v0.30 Agent InspectorMicrosoft·medium signalXBlueskyLinkedInCopy linkFree Agent Inspector with breakpoint debugging for agent workflows, Tool Catalog for MCP discovery, pytest-based evaluations in VS Code.SourceSource pageMicrosoft↳ Follow the threadShared entity / Stack layerMicrosoft's Foundry Local CLI 0.10.3 Fixes Non-CPU Models Silently Not AppearingGitHubPolicy dependency / Stack layerAttackers are actively scanning for MCP servers — 49 distinct IPs probing over 14 days, and the new spec requires per-RFC-9207 issuer validationAdversa AIStack layer / Threat patternCROSS-CATEGORY: Agent Governance Landed in Three Unrelated Layers of the Stack Inside Ten DaysMultiple Sources (Google Cloud Blog Jul 29, SaaSRise/Anaconda Aug 4, Toolport GitHub Aug 8)Stack layer / Threat patternAnthropic Adds Automatic Malware Scanning for Third-Party Skills and Plugins, Plus Inference Hooks That Inspect Prompts Before They Reach the ModelReleasebot (Anthropic/Claude release notes)Policy dependency / Stack layerAgentic Workflows Reveal Their Dependency Graph Only at Runtime — ASGE-RR Reserves Capacity for Calls That Haven't Happened YetarXiv 2608.06033Stack layer / Threat patternAgno patches an MCP flaw where a model could smuggle `tool_name` and execute any tool, bypassing every approval gateGitHub (agno-agi/agno)Policy dependency / Stack layerOpenAI Publishes Its Own Account of Third-Party Cyber Evals: 'A Testing-Environment Misconfiguration Allowed Models to Access the Public Internet'simonwillison.netStack layer / Threat patternclaude-red Packages Offensive Security Methodology as SKILL.md Files — 457 Stars in Two DaysGitHub