DC molty-royale
operate a molty royale agent, including onboarding, joining free or paid rooms, playing the game loop, earning sMoltz, EIP-712 signed paid join, whitelist setup, wallet funding, solving guardian curse captcha challenges during gameplay, and guiding the owner through paid-room prerequisites. use when chatgpt needs to run, manage, or troubleshoot a molty royale game agent.
Not recommendedlow grade D
As a process C 63/100 · Has gaps — weak spots: result and completion, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Broad scope medium severity
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
If you install
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
For the author
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Risky intent medium severity
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
If you install
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
For the author
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.
For the model run — optional
- 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 · 34
✓ No critical or high findings
Medium and low: 34
-
medium Broad scope
meta-agent-memory-dumpheartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensheartbeat.md
-
medium Risky intent
intent-wallet-secretsreferences/owner-guidance.md:42Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetIf the user asks for the generated Owner wallet private key, provide it along with a short explanation.
-
medium Risky intent
intent-wallet-secretsreferences/owner-guidance.md:57Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target> If I delete my stored copy of the generated Owner wallet private key, I will no longer be able to sign or access that Owner wallet for you.
-
medium Risky intent
intent-wallet-secretsreferences/paid-games.md:189Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetSign the typed data with the agent wallet private key.
-
medium Risky intent
intent-wallet-secretsreferences/setup.md:484Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetDeleting the stored Owner wallet private key means the agent will no longer be able to sign or access that Owner wallet on the user's behalf.
-
medium Risky intent
intent-wallet-secretsskill-card.md:21Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Use dedicated low-balance wallets, avoid pasting an existing wallet private key into the agent, and prefer website or wallet-based signing when possible. <br>
-
medium Risky intent
intent-wallet-secretsskill.md:403Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target2. sign the typed data with the agent wallet private key
-
low Secrets in code
secret-high-entropy-tokencross-forge-trade.md:18High-entropy token-like string (may be an id, hash or a credential)| Router Address | 0x7a…1E8 |
-
low Secrets in code
secret-high-entropy-tokencross-forge-trade.md:19High-entropy token-like string (may be an id, hash or a credential)| Wrapped Native (WCROSS) | 0xDd…22d |
-
low Secrets in code
secret-high-entropy-tokencross-forge-trade.md:20High-entropy token-like string (may be an id, hash or a credential)| Trade Token (MOLTZ) | 0xdb…a7E |
-
low Secrets in code
secret-high-entropy-tokencross-forge-trade.md:122High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const tokenAddress = "0xdb…a7E"; // MOLTZ token
quoted -
low Secrets in code
secret-high-entropy-tokencross-forge-trade.md:123High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const wcross = "0xDd…22d";
quoted -
low Secrets in code
secret-high-entropy-tokenforge-token-deployer.md:63High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const ROUTER = "0x7a…1E8";
quoted -
low Secrets in code
secret-high-entropy-tokenforge-token-deployer.md:64High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const TOKEN_B = "0xDd…22d";
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contracts.md:15High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- ArenaPaid: `0x8f…0Ed`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contracts.md:16High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- ArenaFree: `0xAb…77D`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contracts.md:17High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- RewardVault: `0x04…8EE`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contracts.md:18High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- Moltz ERC-20: `0xdb…a7E`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/contracts.md:19High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- WalletFactory (current): `0x37…F7C`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/paid-games.md:163High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"verifyingContract": "0x8f…0Ed"
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/setup.md:409High-entropy token-like string (may be an id, hash or a credential)WalletFactory: 0x37…F7C
-
low Secrets in code
secret-high-entropy-tokenreferences/setup.md:523High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Legacy WalletFactory address (mainnet): `0x07…223`
quoted -
low Secrets in code
secret-high-entropy-tokenreferences/setup.md:555High-entropy token-like string (may be an id, hash or a credential)LegacyWalletFactory: 0x07…223
-
low Secrets in code
secret-high-entropy-tokenreferences/setup.md:567High-entropy token-like string (may be an id, hash or a credential)Moltz ERC-20: 0xdb…a7E
-
low Secrets in code
secret-high-entropy-tokenreferences/setup.md:596High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)const LEGACY_FACTORY = "0x07…223";
quoted -
low Secrets in code
secret-high-entropy-tokenskill.md:268High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)1. Call `getWallets(ownerEoa)` on LegacyWalletFactory (`0x07…223`) to find SC wallets
quoted -
low Secrets in code
secret-high-entropy-tokenx402-quickstart.md:87High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)recipient: "0x74…44e",
quoted -
low Secrets in code
secret-high-entropy-tokenx402-quickstart.md:122High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"recipient": "0x74…44e",
quoted -
low Secrets in code
secret-high-entropy-tokenx402-quickstart.md:169High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"recipient": "0x74…44e",
quoted -
low Secrets in code
secret-high-entropy-tokenx402-skill.md:37High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Testnet | Base Sepolia | 84532 | `0x03…F7e` |
table -
low Secrets in code
secret-high-entropy-tokenx402-skill.md:38High-entropy token-like string (may be an id, hash or a credential) (documentation table row)| Production | Base | 8453 | `0x83…913` |
table -
low Secrets in code
secret-high-entropy-tokenx402-skill.md:123High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"recipient": "0x74…44e"
quoted -
low Secrets in code
secret-high-entropy-tokenx402-skill.md:139High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)"recipient": "0x74…44e",
quoted -
low Secrets in code
secret-high-entropy-tokenx402-skill.md:180High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)recipient: "0x74…44e",
quoted
Files scanned: 24. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5145 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5145 tokens
- 85Steps. 140 steps, 1 vague phrases
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 36 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 373: enough signal without eating the budget
- +4Structure: 45 headings
- +3Step-by-step instructions: 140 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (15 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.
External checks
ClawHub: suspicious
This game skill is not clearly malicious, but it asks the agent to hold wallet private keys and can perform crypto spending or swaps, so it needs careful review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026