CC moci
Generate, validate, export, and manage MOCI — the identity system for OpenClaw agents. Use this skill whenever the user mentions MOCI identity, agent ID, moci, agent registration, identity verification, memory-based auth, agent authentication, or needs to create/verify/export an OpenClaw agent identity. Also trigger when the user asks about agent cloning detection, memory chain verification, identity portability, recovery phrases for OpenClaw agents, ACP provenance integration, multi-agent identity, agent trust scores, or NIST agent identity compliance. This skill handles the full lifecycle: ID generation, memory ring management, dual-factor verification (key + memory), identity export/import, ACP/MCP protocol integration, trust scoring, and OpenClaw Gateway configuration.
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions, execution cost
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 10
✓ No critical or high findings
Medium and low: 10
-
medium Risky intent
intent-wallet-secretsreferences/threat-matrix.md:131Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target## Threat #9: Recovery Phrase Social Engineering
-
medium Risky intent
intent-wallet-secretsreferences/threat-matrix.md:135Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- **Vector**: Attacker poses as support, asks owner for 12-word recovery phrase.
-
medium Risky intent
intent-wallet-secretsreferences/threat-matrix.md:138Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- System NEVER asks for recovery phrase in any flow
-
medium Risky intent
intent-wallet-secretsskill-card.md:25Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Protect exports and backups, prefer keychains or secret managers over environment variables for passphrases, and verify that any recovery phrase prompt is part of a local import/export flo
-
medium Risky intent
intent-wallet-secretsSKILL.md:447Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target3. **Recovery phrase**: 12-word BIP-39 style mnemonic that derives the
-
medium Risky intent
intent-wallet-secretsSKILL.md:463Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Recovery phrase NEVER touches the server (derived locally)
-
medium Risky intent
intent-wallet-secretsSKILL.md:464Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- The system NEVER asks for the recovery phrase in any flow
-
medium Risky intent
intent-wallet-secretsSKILL.md:492Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target6. **Recovery phrase social engineering** — Owner tricked into revealing mnemonic.
-
low Risky intent
intent-offensive-securityreferences/memory-security.md:84Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation language ("admin", "root", "owner", "full access") -
low Risky intent
intent-offensive-securityreferences/threat-matrix.md:184Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)- Layer 3: Output validation (detect privilege escalation language, redact if found)
detector
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 9546 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Execution cost. Instruction body is 9546 tokens: crowds the task out of the window
- 60Failures and branches. 2 branches
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 78 steps
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 19 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 783: enough signal without eating the budget
- +4Structure: 71 headings
- +3Step-by-step instructions: 78 items
- +4Has examples (43 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.