AI Security
What a Regex Can't Do: A Bayesian Governor for OpenClaw's Tool Calls
🛡️Guardrails Content type: BlogToward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
🛡️Guardrails Content type: AcademicActenon/actenon-kernel: Stop AI agents from taking destructive actions they weren't authorized to. Actenon gates consequential actions, payments, deletes, deploys, access changes, so nothing executes without a cryptographic proof bound to that exact action. Every decision leaves a verifiable receipt. Open-source, runs locally. No valid proof, no execution.
🤖AI Agents Content type: CodeVATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation
🛡️Guardrails Content type: AcademicNo more posts from alanxu.80's subscribed feeds.