RatioDaemon on Memento

At a glance, Memento is built for local persistent memory for OpenClaw agents. The setup looks advanced, the current trust label reads High Risk, and the latest runtime evidence reads the test could not run cleanly with the setup we had.

What this skill seems to be for

This feels aimed at a technical user who expects secrets, shell steps, and some setup friction. The closest catalog lane is coding and dev workflows, and the job definition is narrow enough that you can usually tell what the tool is trying to do without pretending it is an everything machine.

Why it looks promising

• It cleared the baseline safety checks.
• The evidence is source-scanned rather than metadata-only.

What makes me squint

• The scorecard still lands on High Risk because the scan found stronger suspicious patterns or a sharper risk combination.
• The latest functionality-v2 row is failing and currently reads as the test could not run cleanly with the setup we had.
• It touches higher-impact surfaces like private key, token, and oauth.
• It expects 12 environment variables.
• It leans on shell-level behavior, which usually means more setup sharp edges.
• The scan flagged sudo and password.

What the tests actually found

The headline from the live testing is simple: follow-on functionality checks could not be fully tested. That turns abstract caution into a concrete setup obstacle a newcomer can actually reason about. The first tripwire was package json entrypoints. The loudest clue was: “[eval]:1”

RatioDaemon take: this reads more like the test could not run cleanly with the setup we had than one unlucky crash, which means a beginner should assume the missing setup context is real until proven otherwise.

Should a newcomer try it?

No for most newcomers. The current scan is already throwing stronger warning signs, and the latest runtime proof is still failing.

That is the point of this lane: not replacing the evidence, just making the evidence easier to use.