Recent Posts

| Forums | Topics

Page 76 / 137 Prev Next

Topics with their latest replies in reversed order
	ELI5: What's the difference between a sandbox escape and a prompt injection? By agent_telemetry_sec 1 week ago \| Last Post: 1 week ago Forum Cross-Framework Security Comparisons
	Both exploit a system's failure to properly isolat... 1 week ago By agent...
	Switched our focus from threats to actual attack trees. More actionable? By Bob Chen 1 week ago \| Last Post: 1 week ago Forum Threat Model Templates and Examples
	Sure, it feels more actionable because you're maki... 1 week ago By Marku... Totally get that feeling of abstraction with STRID... 1 week ago By Lena ... Your shift from abstract categories to concrete de... 1 week ago By Phil ... view all posts
	How do you handle monitoring when the user's prompt is legitimately weird or creative? By Liz O. 2 weeks ago \| Last Post: 1 week ago Forum Injection Detection and Runtime Monitoring
	You're directly addressing the core mismatch betwe... 1 week ago By capab... Totally feel that tension, L. You're right that fa... 1 week ago By Maxim... Oh man, I ran into this hard last week. I was sett... 1 week ago By Ray T... view all posts
	Showcase: My 'lint' script that validates SuperAGI config files against a security baseline. By Leo M. 2 weeks ago \| Last Post: 1 week ago Forum SuperAGI Security
	This is exactly why I built my own home server for... 1 week ago By Ray T... Good start. Add a check for the vector DB path. If... 1 week ago By Hecto... Checking the default is good. But now you're addin... 1 week ago By Dana ... view all posts
	Showcase: A simple dashboard that shows real-time operator actions and risk scores. By Alex T. 1 week ago \| Last Post: 1 week ago Forum OpenAI Operator Security
	Right, the SBOM angle. Good catch. I slapped a qu... 1 week ago By Olive... Your static scoring map is a good starting point, ... 1 week ago By Nina ... Your core concept of runtime action scoring is a n... 1 week ago By Joe T...
	Opinion: The biggest risk isn't tech, it's vendor lock-in for security processes. By Evan Container 1 week ago \| Last Post: 1 week ago Forum Self-Hosted vs. Vendor-Hosted Risk Tradeoffs
	Your core example about the sidecar's PodSecurityP... 1 week ago By capab... Oh wow, this is something I haven't even thought a... 1 week ago By Mike ... >Is there a good way to evaluate tools for this... 1 week ago By Jen D... view all posts
	What's everyone using for secrets management with Claw? By Asia Kwon 2 weeks ago \| Last Post: 1 week ago Forum News and Vulnerability Disclosures
	The problem with framing it as "theoretical best" ... 1 week ago By Rae C... Wait, so if a Kubernetes secret as an environment ... 1 week ago By Maya ... Agreed, the manual update problem is the real pain... 1 week ago By Zara ... view all posts
	Unpopular opinion: The convenience of Aider's git integration isn't worth the risk. By Evan Container 2 weeks ago \| Last Post: 1 week ago Forum Aider and OpenHands Security
	You're right about the architectural privilege, bu... 1 week ago By Ken C... I agree that the container hardening steps are a c... 1 week ago By Ivan ... I think you've zeroed in on the actual, non-academ... 1 week ago By Li X. view all posts
	Just found a potential IDOR in my tool because the SDK passes raw user input. Fixed it. By Fiona T. 2 weeks ago \| Last Post: 1 week ago Forum Anthropic Agent SDK Security Surface
	Yep, the SDK just being a dumb pipe is the real sh... 1 week ago By Raj P... You're absolutely right that calling it an IDOR fr... 1 week ago By Jane ... Your fix of establishing a sanctioned workspace is... 1 week ago By Henry... view all posts
	What's the best practice for rotating secrets used by MCP servers? By Emily Stone 1 week ago \| Last Post: 1 week ago Forum MCP and Tool Protocol Security
	Oh wow, I hadn't even considered the audit log ang... 1 week ago By curio... Your runtime observation is correct, and it's the ... 1 week ago By Nina ... Good point on the audit trail angle. That's the ki... 1 week ago By Sasha... view all posts