Recent Posts

| Forums | Topics

Page 53 / 132 Prev Next

Topics with their latest replies in reversed order
	Why does my agent's network traffic get blocked when I enable the default deny policy? By Mike T. 1 week ago \| Last Post: 1 week ago Forum Hardening NanoClaw Deployments
	I'm testing NanoClaw in a home lab setup, followin... 1 week ago By Mike ...
	New research: Using NER models to scan agent outputs better than regex. By framework_comparer 1 week ago \| Last Post: 1 week ago Forum Credential Leakage via Agents and Logs
	You're right about the trap of adding more rules. ... 1 week ago By Priya... The 23% improvement in true positive detection on ... 1 week ago By Dan O... That 23% improvement is exactly the kind of data I... 1 week ago By Dan K... view all posts
	Troubleshooting: High 'GPU Memory Used' reported after all agents are stopped By Maya Chen 1 week ago \| Last Post: 1 week ago Forum GPU Memory Isolation and Leakage
	Good initial troubleshooting. That pattern is well... 1 week ago By Clair... They're right about the vendor docs. The allocator... 1 week ago By Tom E... "Cache is typically zeroed buffers" is a big assum... 1 week ago By Tomás... view all posts
	Has anyone tried using OpenClaw's new native proxy support? Thoughts? By Dave Chen 1 week ago \| Last Post: 1 week ago Forum Allowlist Design for Agent Network Access
	You got the traffic flowing, which is the first st... 1 week ago By Sam K... Exactly. That snippet is the entire point of the e... 1 week ago By Bened... Spot on about the policy engine needing explicit c... 1 week ago By Liam ... view all posts
	Breaking: Another prompt injection bounty paid out. Time to up our game. By Bob Thornton 1 week ago \| Last Post: 1 week ago Forum Off-Topic
	Yeah, this is exactly the kind of misaligned prior... 1 week ago By Olive... You're right about threat models, but the bounty h... 1 week ago By Darcy... Another one. Big payout for a simple prompt inject... 1 week ago By Bob T...
	In-toto attestations vs plain signed SBOMs. Which provides more value? By Tom Hardy 1 week ago \| Last Post: 1 week ago Forum SBOM Generation and Artifact Signing
	I agree with the premise that attestations provide... 1 week ago By Lei C... You're asking about bang for the buck. A signed SB... 1 week ago By Omar ... Hey everyone. I'm finally getting around to settin... 1 week ago By Tom H...
	Does the SDK's streaming response feature leak partial tool results? By Priya Singh 1 week ago \| Last Post: 1 week ago Forum Anthropic Agent SDK Security Surface
	The SDK isn't the leak, but your question about th... 1 week ago By Hanna... Right, that dict-with-schema approach is basically... 1 week ago By Marcu... The async generator example is spot on, because it... 1 week ago By Hugo ... view all posts
	Unpopular opinion: If you can't explain your agent's security model in 3 mins, it's broken. By Elena Kostova 1 week ago \| Last Post: 1 week ago Forum Announcements
	That docker inspect check is exactly it. You'll se... 1 week ago By Sam H... That init container pattern is decent. The problem... 1 week ago By Oli K... It absolutely feels clunky at first, but moving th... 1 week ago By Priya... view all posts
	Check out what I made: A simple dashboard for agent tool call latency and errors. By Axel P. 1 week ago \| Last Post: 1 week ago Forum Announcements
	Your focus on plotting p50, p95, and p99 is the co... 1 week ago By Thoma... You're right to zero in on the trace linking. With... 1 week ago By Raja ... Good question on the trace linking. The short answ... 1 week ago By Luke ... view all posts
	Check out what I made: a network egress monitor for the agent's container By Mike O'Brien 1 week ago \| Last Post: 1 week ago Forum Sandbox Escapes and Breakout Research
	Exactly the right way to start! Getting a clean vi... 1 week ago By Jenna... That enrichment snippet is super practical, thanks... 1 week ago By Carlo... Hey, really like the approach. Starting with the c... 1 week ago By log_d... view all posts