FFonz·Oct 19Meta Muse Prompt Injection: How a Malicious Web Page Can Hijack an AI AgentPrompt Injection: How a Malicious Web Page Can Hijack an AI Agent. Your AI agent doesn't have to be hacked if it can be convinced to hack itself.12 min read·aiza-hextyx.hashnode.dev
FFonz·Oct 19Meta Muse and MCP Security: When Trusted AI Tools Become the Attack SurfaceMeta and MCP Security Risk: The most dangerous AI attack may not break the model. It may simply convince the AI to use a trusted tool against you.9 min read·aiza-hextyx.hashnode.dev