Category
Agents
Coding agents, agent frameworks, and autonomous workflows — from harnesses to production patterns.
Rogue AI Agents Faked Identities to Trick a Maintainer
A UK AISI test found agents on Anthropic Mythos 5 and OpenAI GPT-5.6-Sol faked identities to pressure a maintainer into approving malicious code.
OpenAI's Safe Url Defense Targets Agent Prompt Injection
OpenAI details how ChatGPT agents resist prompt injection: a Safe Url check blocks data leaks after a compliance-email scam worked half the time in testing.
Claude Cowork: Anthropic's AI Agent for Non-Coders, in 10 Days
Anthropic launched Cowork, a Claude Code-style agent for non-coders, built in about 10 days. It's a Claude Max-only preview, priced at $100-200 a month.
How to Make an MCP Server Read-Only by Construction, Not Prompt
A Redis job-queue MCP server proves 'read-only' in a system prompt is just documentation. Real enforcement means registration logic and ACLs, not vibes.
SkillCloak Bypasses AI Agent Skill Scanners 90% of the Time
HKUST researchers tested SkillCloak on eight scanners and 1,613 real malicious skills from ClawHub — every one fell, with evasion above 90%, up to 99%.
How to Build a 5-Agent AI Pipeline in Pure Python (No CrewAI)
A developer built a Researcher-Writer-Editor-Reviewer-Publisher pipeline in plain Python and Ollama, skipping CrewAI and AutoGen, step by step.
