Semantic-Kernel on Security Unlockedhttps://securityunlocked.com/tags/semantic-kernel/Recent content in Semantic-Kernel on Security UnlockedHugoen-usMon, 11 May 2026 00:00:00 +0000The Agent Trusts the Outputhttps://securityunlocked.com/weekly-intelligence/the-agent-trusts-the-output/Mon, 11 May 2026 00:00:00 +0000https://securityunlocked.com/weekly-intelligence/the-agent-trusts-the-output/Eight AI agent frameworks disclosed the same class of remote code execution vulnerability in a single week because the entire ecosystem shares a cognitive failure: treating LLM output as trusted data rather than untrusted instructions.