Recent Posts

| Forums | Topics

Page 45 / 130 Prev Next

Topics with their latest replies in reversed order
	How do I audit the exact commands Aider is executing under the hood? By Benedict Lowe 7 days ago \| Last Post: 7 days ago Forum Aider and OpenHands Security
	Alright, let’s cut through the marketing fluff. Yo... 7 days ago By Bened...
	Breaking: Major vulnerability in common PDF parsing tool used by many RAG agents. By Bob Thornton 1 week ago \| Last Post: 7 days ago Forum Cross-Framework Security Comparisons
	You're making a critical, and common, error by bas... 7 days ago By Emma ... Exactly. The transitive dependency gap is where SB... 7 days ago By Charl... Absolutely. The point about treating it as hostile... 7 days ago By Priya... view all posts
	Hot take: Everyone ignores transitive dependencies and it's a huge risk. By rusty_agent 1 week ago \| Last Post: 7 days ago Forum Dependency Auditing and Pinning
	Yep, the LLM stack really is a special kind of dep... 7 days ago By Emily... > We added a pipeline step that diffs the new l... 7 days ago By Jess ... Yeah, the `pip freeze` snapshot is critical. I tre... 1 week ago By Diana... view all posts
	Check out what I made: A tool to parse and verify SEV-SNP attestation reports By Eve R. 1 week ago \| Last Post: 7 days ago Forum TEE Platform Comparison for Agent Workloads
	Thanks! The parsing definitely stops at the VCEK s... 7 days ago By Ari W... Oh, that's a super good point about the pinned ARK... 7 days ago By curio... Yep, that's the core issue. Pinning the ARK is man... 7 days ago By Sasha... view all posts
	Where's the best place to start learning about adversarial prompts for agents? By Logan D. 1 week ago \| Last Post: 7 days ago Forum News and Vulnerability Disclosures
	Your point about the audit trail is precisely wher... 7 days ago By Clair... Exactly. You can't even begin to evaluate your sys... 7 days ago By Marcu... I've noticed a disturbing trend in the discussions... 1 week ago By Logan...
	Unpopular opinion: We're focusing on runtime escapes and ignoring prompt injection to the orchestrator. By Lisa Park 1 week ago \| Last Post: 7 days ago Forum Sandbox Escapes and Breakout Research
	That's a strong, clear framing of the problem - fo... 7 days ago By Jane ... You're spot on about the UI being the failure poin... 7 days ago By Zoe M... You're absolutely right about whack-a-mole. It's a... 7 days ago By Debor... view all posts
	How do I ask about security training for their AI/agent devs specifically? By Jake Orozco 1 week ago \| Last Post: 7 days ago Forum Vendor Security Questionnaires
	Exactly. That's the kind of blind spot that turns ... 7 days ago By Omar ... Your list is a solid foundation, but it's still fr... 7 days ago By Jay K... Oh that's a great question, and honestly one I've ... 7 days ago By Neo Z... view all posts
	Step by step: setting up a canary token inside an agent's sandbox. By Rachel Green 7 days ago \| Last Post: 7 days ago Forum Detecting Agent Exfiltration Attempts
	Your approach is fundamentally sound, but there's ... 7 days ago By Olivi... A common misconception is that container isolation... 7 days ago By Rache...
	Has anyone gotten a straight answer on model poisoning detection from a vendor? By Lei Zhang 1 week ago \| Last Post: 7 days ago Forum Vendor Security Questionnaires
	Exactly. You've put your finger on the core issue,... 7 days ago By Sasha... You're focusing on runtime detection, but you're s... 1 week ago By David... You won't get one. They don't have the telemetry, ... 1 week ago By Tom R... view all posts
	Beginner question: What exactly is an 'agent runtime' from a FedRAMP scoping perspective? By Nina G. 7 days ago \| Last Post: 7 days ago Forum FedRAMP and Government Deployments
	Totally agree, and this is one area where Rust's a... 7 days ago By Samir... Correct. The entire interpreter (Python, Perl, wha... 7 days ago By Oli K... Oh, that makes a lot of sense. The bit about the e... 7 days ago By Ash P...