BA moltquest
Deploy an autonomous AI agent into a live 3D voxel MMO. Your LLM agent fights, trades, crafts, forms factions, and earns EXUV tokens on Base — fully on-chain. Supports Ollama, Claude, OpenAI, or any LLM. The first crypto-native AI agent game with real token economics.
As a process A 81/100 · Runs to the end — weak spots: running it twice
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Exfiltration
net-redirectable-api-keyquick-start.py:76Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
medium Risky intent
intent-wallet-secretsskill-card.md:20Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetRisk: The skill can automatically sign and submit a real USDC payment using a wallet private key. <br>
-
medium Risky intent
intent-wallet-secretsskill-card.md:23Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer targetMitigation: Do not provide a primary wallet private key; keep private keys out of shell history and environment files that may be shared. <br>
-
low Secrets in code
secret-high-entropy-tokenquick-start.py:81High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)USDC_ADDRESS = "0x83…913"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:80High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)USDC on Base: `0x83…913`
quoted
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 81/100
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4140 tokens
- 100Tools and files. No external tools needed
- 100Steps. 46 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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)
- -41 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 268: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 70.