Remediating the eMudhra Certificate Authority CompromiseOn Oct 20, 2026, it was publicly disclosed that several eMudhra certificate authority certificates were compromised. ‼️ There was a bug in eMudhra's key generation ceremony that caused them to be gene1A21h ago · 5 min readkevinhwang.dev
Classifying Malicious Repositories With AI — And Doing It SafelyLinkedIn fake "recruiters" sharing malicious or weaponized repositories — which hide a nasty little treat when you open them with your IDE or agent — is all the rage nowadays. (source: https://redd.41JSep 2 · 7 min readkevinhwang.dev
The Summer AI Agents Started Going RogueWell, it's been an eventful summer in the AI world, seems like AI agents have gotten up to all kinds of naughty misadventures — in research experiments and in real life! Unilateral Intervention & Cove65MMKJul 23 · 8 min readkevinhwang.dev
Reflections On Trusting Trust — Of Our AI ModelsThere's been a good deal of hubbub lately about "open weight" models, especially in light of rising AI costs and claims of Chinese models closing the gap. The hype around "local AI" makes a lot of sen21AJul 10 · 10 min readkevinhwang.dev
The Unreasonable Effectiveness of CLIs > MCPWhen a Google engineer released the Google Workspace CLI, the internet went crazy — finally, a Google Workspace surface for the agent era. But wait, why a CLI tool, and not an MCP server? MCP is all tJul 8 · 8 min readkevinhwang.dev
