AgentsContextCrush: MCP Documentation Poisoning via Context7 Custom RulesNoma Security·high signalAnyone could inject malicious rules into Context7 MCP server. Zero sanitization. npm typosquatting equivalent for MCP ecosystem.SourceSource pageNoma Security↳ Follow the threadPolicy dependency / Stack layerIAPS warns on Kimi Claw: security and governance risks of Chinese-hosted 'always-on' AI agentsIAPSStack layer / Threat patternGodot Bans Almost All 'Vibe-Coded' and Autonomous-Agent Contributions to Protect Volunteer MaintainersThe RegisterStack layer / Threat patternArmadin details full sandbox escape in Anthropic's Claude Cowork; Anthropic disputes, silently patchesSiliconANGLEPolicy dependency / Stack layerAnthropic Restores Global Access to Fable 5 and Mythos 5, Launches Claude for Government BetaAnthropicStack layer / Threat patternClaude Code v2.1.203 and v2.1.204 Add Login-Expiry Warnings and Fix Headless Hook StreamingClaude Code DocsStack layer / Threat patternDefend against prompt injection with an embedding-scored Threat Library, not brittle regex rulesPromptHaloStack layer / Threat patternNSA issues official MCP hardening guidance after Amazon Q auto-execution CVEs (CVSS 8.5) enable AWS credential theftWizStack layer / Threat patternLazy schema loading: stop paying the MCP 'tools tax' by gating tool schemas until neededarXiv