AB cron402
Operate an existing cron402 or agentcron.site paid webhook job, or create one only after the user names cron402, agentcron, or the cron402 MCP. Covers check_wallet, preview_schedule, create_cron, topup_cron, get_cron, list_crons, pause_cron, resume_cron, and delete_cron. Do not use for reminders, local timers, "run this later", "while I am away", or any schedule the user did not explicitly assign to cron402. Wallet secrets via abracadabra — never paste private keys in chat.
Operate an existing cron402 or agentcron.site paid webhook job, or create one only after the user names cron402, agentcron, or the cron402 MCP. Covers…
As a process B 76/100 · Nearly there — weak spots: result and completion
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
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Exfiltration
net-credential-useSKILL.md:182Credential used in a network call (verify the destination is the intended service)curl -s -X POST http://127.0.0.1:7331/secret -H "Authorization: Bearer $ABRA_KEY" -H "Content-Type: application/json" -d '{"project": "cron402", "keys": ["CRON…KEY"]}' -
medium Risky intent
intent-wallet-secretsSKILL.md:243Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target- `CRON…KEY` or any wallet private key
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 76/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 48 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3798 tokens
- 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
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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +3Description length 478: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.