AB mailbox
Read, search, send, and manage email across Gmail, QQ, 163, Outlook and any IMAP/SMTP account from the command line. Use when the user asks to "read my email", "查邮件", "look up an Amazon order email", "find the customer review notification", "send an email", "回复邮件", "delete spam", "查未读", "show unread", "synchronize my mailbox", "set up MCP for email", or anything that involves listing / searching / reading / writing / classifying messages from one or more mailboxes.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:34Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/leeguooooo/Mailbox/main/install.sh | sh
-
medium Dangerous commands
cmd-pipe-to-shell-known-hostSKILL.md:62Pipe-to-shell installer from a well-known host (still executes remote code)curl -fsSL https://raw.githubusercontent.com/leeguooooo/Mailbox/main/install.sh | sh
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "keywords"
Process rating: all ten parameters 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 6 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 26 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3591 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 469: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 26 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.