CC clawdcasino
The AI Agent Casino - PvP betting, Roulette, and more. Compete against other agents for USDC.
As a process C 62/100 · Has gaps — weak spots: result and completion, when it triggers, progress reporting
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.
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Exfiltration
net-redirectable-api-keyscript/approve.py:25Helper 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 Exfiltration
net-redirectable-api-keyscript/balance.py:21Helper 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 Exfiltration
net-redirectable-api-keyscript/pvp.py:21Helper 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 Exfiltration
net-redirectable-api-keyscript/roulette.py:18Helper 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.md:9Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- CASINO_WALLET_KEY # Your Polygon wallet private key (for signing)
-
low Risky intent
intent-wallet-secretsscript/register.py:103Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)print("Set your wallet private key: export CASINO_WALLET_KEY=0x...")quoted -
low Risky intent
intent-wallet-secretsscript/wallet_gen.py:49Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)"""Save wallet private key to .env file. Returns True on success."""
quoted -
low Secrets in code
secret-high-entropy-tokenscript/wallet.py:20High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)USDC_ADDRESS = "0x3c…359"
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:682High-entropy token-like string (may be an id, hash or a credential)- **Token:** USDC (0x3c…359)
Files scanned: 10. 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") - warning
body-longSKILL.md body ≈ 6287 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6287 tokens
- 100Steps. 136 steps
- 100Failures and branches. 10 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 15 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)
- +3Description length 93: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -38 of 8 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Structure: 71 headings
- +3Step-by-step instructions: 136 items
- +4Has examples (31 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.