AC phishguard
Is this link safe or a scam? Paste any URL from LINE, SMS, or email to instantly detect phishing, fraud, or fake websites. 🚨 Identify scam links before you click 🔍 Detect phishing pages (fake Shopee, bank, login sites) ⚡ Real-time check against 2.5M+ scam domains Powered by 38 global threat intelligence sources, including Taiwan 165, PhishTank, and CERT.PL. 防詐騙網址檢查：貼上任何可疑連結（LINE、簡訊、Email），立即辨識是否為詐騙或釣魚網站。 🚨 點擊前先檢查，避免被騙 🔍 辨識假購物、假銀行、假登入頁 ⚡ 即時比對250萬+詐騙資料（含台灣165等38來源） Example: Input: https://shopee-tw-login-check.com Output: 🚨 Scam detected Reason: Fake Shopee login page (Phishing) Input: https://bank-secure-verification.com Output: ⚠️ High risk Reason: Suspicious domain (Reported by CERT) Input: https://google.com Output: ✅ Safe Reason: No scam or phishing records found Use cases: - Is this LINE link a scam? - Check suspicious SMS links - Verify email phishing URLs - Detect fake shopping or banking sites
As a process C 60/100 · Has gaps — weak spots: inputs and preconditions, consistency, running it twice
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 · 0
✓ No critical or high findings
Files scanned: 4. 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 60/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 40Consistency. Frontmatter name (phishguard) differs from the folder (anti-scam-guard)
- 60Tools and files. Uses tools (bash, web) 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
- 70Failures and branches. 5 branches
- 100Steps. 20 steps
- 100Execution cost. Instruction body is 878 tokens
- 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
- +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 927: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 14 headings
- +3Step-by-step instructions: 20 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.