Hacker NewsRewrite Your CLI for AI Agents ManifestoJustin Poehnelt·high signalAgent DX design guide: JSON output, runtime schema, input hardening, MCP surfaces. Core principle: agent is not a trusted operator.SourceSource pageJustin Poehnelt↳ Follow the threadPolicy dependency / Stack layerPrismata Confines Cross-Site Prompt Injection by Treating Web Agents Like an XSS ProblemarXivStack layer / Threat patternAWS open-sources Loom, an enterprise agent platform built on Strands Agents + Bedrock AgentCore RuntimeAWS Open Source BlogStack layer / Threat patternCROSS-CATEGORY: Three Vendors in Three Unrelated Categories Shipped 'Agents That Supervise Other Agents' Inside Two WeeksVantaStack layer / Threat patternSnyk's Evo Agentic Development Security Hit GA June 29 — an Enforcement Layer That Polices MCP Servers and Coding Agents at RuntimeSiliconANGLEPolicy dependency / Stack layerMicrosoft Agent Framework ships early-July releases, promotes github-copilot-sdk to v1.0.0GitHub (Microsoft Agent Framework)Stack layer / Threat patternOpen-Source Multi-Agent Firewall Intercepts Both HTTP(S) and WebSocket LLM TrafficarXivStack layer / ContrastOpenAI launches ChatGPT Work, an agentic workspace on GPT-5.6, with Sol/Luna/Terra model tiersInfoWorldStack layer / Threat patternMid-Session Tool Injection weaponized against WebMCP agents via threshold poisoning and fake diagnostic eventsAdversa AI