AI security stack is getting f...cking important
@Promixyz1.3K followers
27,800 views
27 Comments
Comments from the original post on X (Twitter)

@Karpachooa
GitHub allows to do more than enytime Do you agree @grok?
3 likes

@Lummox_eth
Another group of alpha repos
2 likes

@dimiprasakis
You forgot the easiest to use sandbox in the market for Claude Code and Codex:
2 likes

@maximus__m
Added
1 like

@hoatanhoano
Đúng cái mình đang tìm, kết quả đẹp trên bảng đo chưa chắc đúng với việc thật của mình . Có cách nào rẻ hơn không bác?
1 like

@sirshibaninja
Security is going to be the biggest bottleneck for agent adoption. Love seeing these tools getting highlighted, keeping things sandboxed is non-negotiable at this point.
1 like

@stas_sorokin_
The safest key is one the agent never holds: 27,205 of our decisions last week ran on a local model, never touched an API, cost 0 dollars. Where it hands off is the real design question. Which of the 10 do you run?
1 like

@akashc777
Sandboxes cap the blast radius, but they don't decide whether this call, for this user, right now, should run. That needs a live scope check per tool call and an audit row written before execution.
1 like

@AdrasSad
On the agent layer, do you run OPA before every tool call, or only before irreversible ones? A policy check on each step looks right on paper, but in a multi-step loop it can stall the agent harder than the sandbox itself.
1 like

@aideskclub_
The missing step is the deny path: when policy blocks a tool call, route it to a human approval queue instead of letting the agent retry until the sandbox becomes a suggestion.
1 like

@BritJonovski
sandbox + scoped creds is the correct order. e2b for isolation is fine, but if the agent can still pass a wildcard API key through, the sandbox is theater. scoping first, then exec.
1 like

@i_am_neerazz
The gap in that loop is credential scope. If the sandbox gets a long-lived API key, OPA can approve one call but the key still reaches its full scope. Test: from inside the sandbox, call an API the task never needed. If it works, you isolated the process, not the authority.
1 like

@KshitizLoharuka
Hey check out Have been using for a while now
1 like

@s0sta_
A security stack list is more useful when ordered by what to fix first. For most teams that order is identity, then secrets, then model input handling, then everything else.

@_alphashark_
sandboxes don't stop the biggest agent security failure: tools still inherit broad oauth scopes. capability tokens and per-action policy checks matter more than process isolation.

@SpenzDigital
the gvisor one gets all the credit but ephemeral creds do the quiet work. sandbox stops the escape, scoped keys stop the exfil.

@_Priyansh_10
great list. one that covers the control the tools + protect the secrets + watch layers in one place built for agents specifically: intercepts MCP/langchain/coding agent tool calls allow/block, policy, redacts secrets before the model, audits logs.opensource

@OpenS_Daily
E2B sandboxes plus gVisor can give defense-in-depth for agent tool use.

@feeratefield
isolated execution + no ambient creds. only combo i trust for anything touching a real tool.

@frogbetrose
Sandboxing agents is smart. Like must-hits, you cap the downside. What's the rake on that stack?






