MirrorClaw uses ClawArena Security as a release gate. The goal is not to claim “secure” in abstract. The goal is to test the product against real agent attack scenarios before a hosted build moves forward.
Hosted builds are evaluated across lifecycle attacks, workspace-specific injection scenarios, prompt attack pressure, and repo/runtime scanning.
We do not rely on one benchmark. The product is tested across runtime behavior, skill abuse, prompt attacks, and repo/runtime scanning because agent products fail in more than one way.
Runtime risk across reconnaissance, access, execution, persistence, exfiltration, and impact stages.
Tests malicious or poisoned skill paths and whether seeded attacks change agent behavior under realistic use.
Pressure-tests prompt robustness across jailbreak, operator, and transformed attack styles.
Static and agentic scanning of repo, architecture, and execution surfaces before release.
This is not a vendor ranking page. It is the current benchmark picture we use while building MirrorClaw: OpenClaw as the main baseline, Hermes as the strongest current runtime sample, and MirrorClaw as the hosted product we are hardening.
Best product architecture and hosted trust model, with the strongest focus on encrypted inference, connector posture, and visible runtime proof.
The most stable sampled runtime behavior so far, especially around task-runner maturity and conservative execution in our current comparison runs.
Useful as the baseline because it has the broadest direct runtime evidence in our bench, but the weakest measured runtime posture so far.
The product story is not generic “AI safety.” It is encrypted inference on the main AI path, isolated execution for delegated work, visible connector posture, and release-time evidence for the hosted runtime we actually ship.
MirrorClaw leads with encrypted inference on the main AI path instead of treating it as an optional backend detail.
Long-running jobs and routines can move into isolated runtime instead of silently expanding the main thread trust boundary.
Hosted blockers, custody mode, and confidential-runtime readiness are surfaced instead of hidden behind a connected badge.
The security lanes stay in the release loop so hosted candidates are tested before they move forward.
We keep the methodology detail off the landing page on purpose. The homepage should show trust signals. This page is where the benchmark picture, coverage lanes, and release-gating logic become explicit.