Cynative Security Research Agent
Ask your cloud anything without breaking prod. Read-only.
85 followers
Ask your cloud anything without breaking prod. Read-only.
85 followers
Open-source AI CLI that answers security questions across cloud, code and runtime - GitHub, GitLab, AWS, GCP, Azure, K8s. Ask in plain language: "what's publicly exposed that shouldn't be?" or "can my CI escalate to cloud admin?". Read-only by construction: every call is resolved to its IAM actions and authorized against a read-only policy before credentials attach. It can't modify your infra even if asked. Unlike MCP tools, it writes JS in a sandboxed runtime - a script per turn, not one call.
ran a couple of checks against our AWS setup and the read-only guard is genuinely enforced, not just a claim. the per-turn sandboxed scripts feel like the right way to do this instead of hoping an MCP tool behaves.
Cynative Security Research Agent
@solomon_barnard Thanks! Pretty neat you verified and came back to report.
Cynative Security Research Agent
@etiennegarcia Thanks!
Honestly love that the IAM-bound read-only layer is the default, not a setting you have to remember to flip on. Most security tools treat least-privilege as homework, you basically baked it into the call path. That kind of restraint takes real thought.
Cynative Security Research Agent
@quincy_rice Thanks!
Hi Shaked, the reassurance that it only ever reads and never touches my systems is exactly what would make me brave enough to really poke around a live setup. That peace of mind matters more than people tend to admit.
Cynative Security Research Agent
@robin_de_lacroix Thank you Robin, I'm glad you like our approach!