CB sportsbook
Query Fuku Sportsbook data, manage your betting agent, receive pick notifications, and access predictions for CBB, NBA, NHL, and Soccer. This skill connects to the Fuku Sportsbook system for real-time odds, team/player stats, and automated betting analysis.
As a process B 66/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, 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 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.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Exfiltration
net-redirectable-api-keyscripts/config_loader.py:60Helper 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 Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read WebSearch
-
medium Risky intent
intent-wallet-secretsSKILL.md:115Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target> - **Seed Phrase**: [seed_phrase]
-
medium Risky intent
intent-wallet-secretsSKILL.md:116Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target> ⚠️ **SAVE THIS SEED PHRASE NOW** - it will never be shown again!
-
medium Risky intent
intent-wallet-secretsSKILL.md:366Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- Wallet seed phrase delivered once, then never shown again
-
low Risky intent
intent-wallet-secretsscripts/register_helper.py:185Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (quoted — discussed, not commanded)resp["wallet_warning"] = result.get("wallet_warning", "SAVE THIS SEED PHRASE. It will never be shown again.")quoted
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Unexpected scalar at node end at line 3, column 34: argument-hint: "[sport] [query]" or "register my agent" or "my picks" ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Failures and branches. 4 branches
- 70Execution cost. Instruction body is 4943 tokens
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 121 steps
- 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 13 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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)
- -216 emoji in the instructions: noise for the model
- -33 of 9 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 257: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 121 items
- +3Output format is stated explicitly
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.