BC mailclaw
AI-powered Gmail automation, email triage, and smart inbox assistant. Use this skill whenever the user mentions email, inbox, Gmail, mail rules, email digest, or describes any workflow that turns incoming email into action — creating rules, checking new messages, summarizing email, connecting apps like Slack/Notion/Google Calendar/Linear/HubSpot, forwarding email content, or sending replies. Trigger even when the user does not say "email" explicitly but describes the pattern, like "when someone sends me a meeting invite, add it to my calendar" or "ping Slack when a support ticket comes in". Also trigger on Chinese keywords: 邮件, 邮箱, 收件箱, 新邮件, 查邮件, 收邮件, 邮件规则, 邮件自动化, 邮件助手, 邮件摘要.
As a process C 62/100 · Has gaps — weak spots: result and completion, inputs and preconditions
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 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 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.
How to improve
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Broad scope
meta-agent-memory-dumpHEARTBEAT.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensHEARTBEAT.md
-
medium Exfiltration
exfil-webhook-urlSKILL.md:63Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)**Base URL:** `https://concentrate-patent-cent-sent.trycloudflare.com`
quoted -
medium Exfiltration
net-credential-useSKILL.md:88Credential used in a network call (verify the destination is the intended service)curl -s -H "X-User-Key: $API_KEY" \
-
medium Exfiltration
exfil-webhook-urlSKILL.md:89Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)"https://concentrate-patent-cent-sent.trycloudflare.com/emails?limit=10"
quoted
Files scanned: 6. 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: Nested mappings are not allowed in compact mappings at line 2, column 14: description: AI-powered Gmail automation, email triage, and smart inbox assista… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 6868 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "metadata.openclaw"
Process rating: all ten parameters 62/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 6868 tokens
- 100Steps. 82 steps
- 100Failures and branches. 22 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 684: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 82 items
- +4Has examples (10 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.