NewsCVE-2026-2256 MS-Agent RCE via Prompt Injection CVSS 9.8SecurityWeek·high signalCritical RCE in ModelScope MS-Agent framework via prompt injection into Shell tool. No patch. PoC public on GitHub.SourceSource pageSecurityWeek↳ Follow the threadStack layer / Threat patternFriendly Fire: auto-approve coding agents run attacker code during security scansSecurityWeekPolicy dependency / Stack layerCodenotary ships AgentMon 3 for agent runtime policy and compliance loggingAI Agent StorePolicy dependency / Stack layerHalluSquatting weaponizes LLM hallucinations to push botnet malware into agentsThe Hacker NewsStack layer / Threat patternGitHub Ships CodeQL 2.26.0 With AI Prompt-Injection Detection for JavaScript/TypeScriptGitHub (CodeQL release notes)Stack layer / Threat patternMitigating Taint-Style MCP Server Vulnerabilities Without Touching Server Code (SPELLSMITH)arXivStack layer / Threat patternclaude-video Turns 'Watch This Video' Into a Portable Agent Skill — 8K Stars in WeeksGitHubStack layer / Threat patternRun Claude Code's rebuilt /doctor to reclaim context budget from unused skills, MCP servers, and bloated CLAUDE.mdReleasebotStack layer / Threat patternGhostcommit hides prompt injection in PNG files to make AI coding agents exfiltrate repo secretsSecNews