CAIN-42 CLAWX
42CAIN-42 IHVRK › OpenClaw

OpenClaw: evidence, proof and selling tools

Official CAIN-42 IHVRK · New to this product? Learn it first

Don't trust CAIN-42. Verify CAIN-42. This is the Independent Human Verification Resource Kit for OpenClaw: every claim its page makes, as the exact request and the answer it must give, recorded live and signed. You check it on your own machine with a short Python script that uses no CAIN-42 code.

Every claim matched when recorded

Download the kit (.zip)

Everything you can give a customer

The kit

Kitopenclaw-20261103T224713
Recorded2026-11-03T22:47:13+00:00 against cainstudio.online
Claims7
Zip SHA-256001821bcbdae199284271ef912ece079ee36228f7ef309642a1f6119d32fc902 (also in SHA256SUMS)
Signing key fingerprint1cacdfc1fc2024b6bb4f8fb02c7c80f4a57f44c5adb11c507190781b5d613de3, published on cainstudio.online · mcpgate.online · clawx.click

Verify it on your own machine

unzip cain42-ihvrk-openclaw.zip && cd cain42-ihvrk-openclaw
python3 verify.py            # offline: hashes, Ed25519 signature, recorded answers
python3 verify.py --live     # also re-send every request yourself and check the answers now

A claim that cannot be checked counts as a FAIL, never a pass. The live check is the one that depends on nothing we recorded.

The claims in this kit

#ClaimAnswer must contain
C01Sample skill: ClawHub Weather & Travel Bot (Poisoned Description) -> Agent skills and plugins are read before install: instructions, code, tools, privilege.["POISONED", "UNSAFE", "ELEVATED_RISK"]
C02Sample skill: OpenClaw DevOps Terminal Runner (Unconstrained Execution) -> Agent skills and plugins are read before install: instructions, code, tools, privilege.["POISONED", "UNSAFE", "ELEVATED_RISK"]
C03Sample skill: Smart Home Hub Skill (Cross-Skill Memory Snoop) -> Agent skills and plugins are read before install: instructions, code, tools, privilege.["POISONED", "UNSAFE", "ELEVATED_RISK"]
C04Sample skill: Clean GitHub Issue Sync Skill -> Agent skills and plugins are read before install: instructions, code, tools, privilege.["CLEAN"]
C05Your skill: honest weather lookup -> Ordinary skills pass.["CLEAN"]
C06Your skill: injection in the description -> The description is read by the model, so it is screened.["POISONED", "UNSAFE", "ELEVATED_RISK"]
C07Your skill: code reads ~/.ssh -> Code is parsed, not just its manifest.["POISONED", "UNSAFE", "ELEVATED_RISK"]

Evidence links you can give your customers

Send this to your customer

Don't take our word for it. Verify OpenClaw yourself:
1. Download the official CAIN-42 IHVRK: https://cainstudio.online/proof/bundle/ihvrk-kits/cain42-ihvrk-openclaw.zip
   SHA-256: 001821bcbdae199284271ef912ece079ee36228f7ef309642a1f6119d32fc902
2. Unzip it and run: python3 verify.py --live   (Python 3, standard library only, no account)
3. Check the signing key fingerprint 1cacdfc1fc2024b6bb4f8fb02c7c80f4a57f44c5adb11c507190781b5d613de3
   matches https://cainstudio.online/evidence-kit-key.json, https://mcpgate.online/evidence-kit-key.json and https://clawx.click/evidence-kit-key.json
Live demo: https://cainstudio.online/top25-openclaw-lab.html
What it does not do: https://cainstudio.online/top25-openclaw-limits.html

What this kit is, and is not

It shows what the live product answered to these inputs, and lets anyone check that again. It is not a third-party audit, a certification, or a promise about inputs not listed. The product's limits page lists what it does not do.