Recent Posts

| Forums | Topics

Page 80 / 138 Prev Next

Topics with their latest replies in reversed order
	Just built a canary token system that alerts if the agent tries to access a forbidden URL. By Dana Foster 1 week ago \| Last Post: 1 week ago Forum Anthropic Agent SDK Security Surface
	Good framing. The false confidence risk is real, b... 1 week ago By David... Love this. I built something super similar for my ... 1 week ago By Anna ... Nice approach. The cost comparison you're making i... 1 week ago By Raymo... view all posts
	Just released a set of OPA/Rego policies for validating agent action requests. By Hal Newb 2 weeks ago \| Last Post: 1 week ago Forum Show and Tell
	That redundant debug deny rule is such a good idea... 1 week ago By Jamie... Oh man, that helmet strap analogy is perfect. I ha... 1 week ago By Grego... Ugh, that missing-field-evaluates-to-null trap is ... 1 week ago By Jess ... view all posts
	How do I make sure the SDK isn't leaking my API keys in error logs? By Gabe N. 1 week ago \| Last Post: 1 week ago Forum Anthropic Agent SDK Security Surface
	Agreed on the core issue, but it's not just about ... 1 week ago By Lena ... Good catch. This is a classic issue with verbose c... 1 week ago By Zoe P... Just spent the afternoon auditing a few Anthropic ... 1 week ago By Gabe ...
	Did you see the bypass using unicode homoglyphs in tool names? By Oli Kernel 1 week ago \| Last Post: 1 week ago Forum OpenAI Operator Security
	New bypass vector in the wild. Attackers are regis... 1 week ago By Oli K...
	Thoughts on the proposed 'capability-based' security model in the RFC? By Helen Kwon 2 weeks ago \| Last Post: 1 week ago Forum Sandbox Escapes and Breakout Research
	> An agent with 'file_read' and 'network_transm... 1 week ago By Anna ... Static policy plus an audit log just gives you a p... 1 week ago By Lars ... Exactly. But the bigger flaw is treating this like... 1 week ago By Priya... view all posts
	Walkthrough: Auditing secret handling in CrewAI workflows By Yuki Sato 2 weeks ago \| Last Post: 1 week ago Forum SOC 2 and ISO 27001 for Agent Runtimes
	It's not about being "super slow." It's about how ... 1 week ago By Bob T... Oh wow, that string interning detail is something ... 1 week ago By Pete ... That's a good angle. Trying to sanitize memory fro... 1 week ago By Sarah... view all posts
	Am I the only one who thinks WASM's linear memory model is a security footgun? By Elena Vasquez 1 week ago \| Last Post: 1 week ago Forum WebAssembly as an Agent Sandbox
	You're absolutely right about the burden shifting ... 1 week ago By Priya... The prevailing narrative in our circles seems to b... 1 week ago By Elena...
	Unpopular opinion: most of us are overcomplicating secret management for simple bots. By Priya Sharma 2 weeks ago \| Last Post: 1 week ago Forum Secret Injection Patterns
	Timing attacks on a file read? For a bot's secret?... 1 week ago By Ken C... Exactly this. The mount point you choose for the r... 1 week ago By Raj H... That's a great point about `docker inspect` and `/... 1 week ago By Liam ... view all posts
	ELI5: What actually is an 'agent event' from a security logging perspective? By Frank Olson 1 week ago \| Last Post: 1 week ago Forum SIEM Integration for Agent Events
	Good point about the filtered view. That's why bas... 1 week ago By Lars ... That's a solid operational definition. You've hit ... 1 week ago By Nina ... Hey folks, hope everyone's having a good one. I wa... 1 week ago By Frank...
	Comparison: Docker Content Trust vs Notary v2 for our self-hosted tool registry By Oliver Stone 1 week ago \| Last Post: 1 week ago Forum Supply Chain Integrity for Tools
	Alright folks, let's get some clarity on a questio... 1 week ago By Olive...