News for hackers. Stuff that matters.

davidcrowe

Yea, they removed the fork <24 hours after I reported it
Same thing happened to one of my repos in Feb. I wrote up the details with screenshots.

https://reducibl.com/writing/someone-used-my-repo-to-distrib...

Show HN: ACP – Governance for AI Coding Agents (Claude Code, OpenClaw)

https://agenticcontrolplane.com/

Hi. I'm David, founder of Agentic Control Plane (ACP).Last year I connected an app to an LLM with a MCP connector. Turned out that authenticating the LLM user in the app backend was surprisingly hard.That was the canary in the coalmine. If it's hard to authenticate actual users:- what about their agents? - what about downstream governance? Permissions, limits, audit logsACP is a governance...

( Read More... | no comments | on HN )
Re:WebMCP Proposal on Tuesday February 17, 2026 @04:54PM (#47053953)
The difference is that MCP introduces a third party: the agent isn't the user and isn't the service, but it's acting on behalf of one to call the other. Standard HTTP auth assumes two parties. That's the gap the spec needs to address.

Show HN: GatewayStack – Deny-by-default security for OpenClaw tool calls

https://github.com/davidcrowe/openclaw-gatewaystack-governance

I installed OpenClaw and pointed it at a project directory. Within minutes it had read my .env file. I tried adding a permissions skill to lock things down. The agent ignored it. Skills are advisory; the LLM can skip the check or be convinced by a prompt injection to bypass it.So I built a plugin that hooks into before_tool_call at the process level. Checks run on every tool call: identity...

( Read More... | no comments | on HN )