Don't trust AI agents(nanoclaw.dev)

286 points by gronky_ 8 months ago | 166 comments

A sane but bull case on Clawdbot / OpenClaw(brandon.wang)

274 points by brdd 8 months ago | 425 comments

OpenClaw is a security nightmare dressed up as a daydream(composio.dev)

298 points by fs_software 7 months ago | 210 comments

NanoClaw Adopts OneCLI Agent Vault(nanoclaw.dev)

97 points by turntable_pride 7 months ago | 27 comments

How we hacked McKinsey's AI platform(codewall.ai)

420 points by mycroft_4221 7 months ago | 168 comments

CodeWall blog post describing how its autonomous offensive agent found vulnerabilities in McKinsey's internal AI platform Lilli.

Observed Agent Sandbox Bypasses(voratiq.com)

57 points by m-hodges 10 months ago | 40 comments