Kosa8 Labs has printed a 46-page technical report, “Sealed Machines for Autonomous Agents”, benchmarking 11 AI agent infrastructure platforms towards 13 safety necessities it says are vital for deploying autonomous brokers in regulated environments akin to banks, hospitals, defence suppliers and authorities businesses.
The platforms assessed embody Docker, E2B, Modal, Cloudflare, AWS and Google. According to the report’s personal scorecard, no rival system totally met greater than 4 of the 13 necessities. Kosa8 says its personal platform met all 13, although the corporate wrote and carried out the analysis itself, a limitation that deserves editorial weight.
What the report measures
The framework is constructed on a intentionally pessimistic beginning assumption: that an attacker has already gained root entry contained in the agent’s execution atmosphere. From that baseline, the report asks what the compromised agent can nonetheless attain, and whether or not an organisation can reconstruct what it did.
The findings centre on a set of controls that the corporate says most platforms depart unaddressed. These embody enforced two-person approval for high-risk actions at run time, community controls that block locations exterior an outlined coverage (together with uncooked IPv6 and cloud-metadata endpoints), and a tamper-evident audit log appropriate for offline verification by a 3rd celebration.
On efficiency, kosa8 reported a median checkpoint time of 638 milliseconds and a rewind time of 520 ms for a operating agent machine, together with reminiscence and processes. Eight assault situations had been examined, overlaying exfiltration via a poisoned GitHub difficulty, a malicious npm package deal looking for SSH keys, and an MCP instrument “rug pull”. The firm says kosa8 contained or totally dealt with all eight.
The report is candid about shortcomings. Sandbox creation takes round 4 seconds, slower than the warm-pool begins out there from hosted cloud companies. One restore path has an unexplained gradual mode. The firm doesn’t but maintain a SOC 2 report or an impartial penetration check, each of which regulated monetary establishments will usually require earlier than procurement sign-off.
“Every week brings a new story of an AI agent deleting a database or leaking a token, and the industry’s answer has been better prompts and smarter filters,” mentioned Dhruvit Talati, founder and chief government of kosa8. “Putting every agent in a sealed machine is now common. What regulated organisations are missing is control and evidence on their own hardware.”
Regulatory and market context
The report arrives at a second when monetary regulators are starting to border expectations round agentic AI. The FCA‘s ongoing AI technique and the Bank of England‘s mannequin threat steerage each emphasise explainability and auditability, necessities that map straight onto the audit-log and rollback options kosa8 is positioning as differentiators. Under DORA, EU monetary establishments face binding necessities on ICT threat administration and incident response that stretch, in precept, to third-party AI tooling.
The aggressive panorama for AI agent infrastructure in regulated sectors is nascent however filling shortly. Established cloud suppliers are extending their sandbox and secrets-management companies towards agent workloads, whereas a cohort of specialist startups is constructing purpose-built safe execution environments. Kosa8’s declare to differentiation is the mix of hardware-level isolation, run-time coverage enforcement and verifiable audit trails on non-public or air-gapped infrastructure, a profile that speaks to corporations cautious of sending delicate workloads to a shared public cloud.
The firm is ready to launch publicly on Product Hunt on 20 October 2026. Independent verification of the benchmark methodology and a third-party penetration check would be the subsequent credibility milestones the market will look for.
AI degree 1 of 5: written by Darlyn Ho; AI helped with tone, construction or wording; edited and signed off by Mark Walker, Editorial Director. What the levels mean
