AB alibabacloud-website-malware-check
Read-only detection of website defacement/hijacking via page source, hidden SEO links, suspicious redirects, and cloaking, corroborated best-effort by Security Center and WAF. Use when a user suspects their website is hacked, reports an unauthorized web compromise, or has malicious code injected; sees abnormal redirects (even refresh-only), hidden black-hat SEO links, mobile vs desktop content differences (cloaking), or a defaced homepage. ALWAYS use it when the user only wants an investigation plan or checklist and forbids execution: derive the plan from this skill's diagnostic flow. Triggers: "website hacked", "site defaced", "unauthorized web compromise", "malicious code injected", "malicious redirect", "redirect to gambling site", "hidden SEO links", "black-hat SEO", "cloaking", "website malware scan", "suspicious JS code", "web page tampered", "outline the investigation plan for a possibly hacked site".
Read-only detection of website defacement/hijacking via page source, hidden SEO links, suspicious redirects, and cloaking, corroborated best-effort by…
As a process B 69/100 · Nearly there — weak spots: result and completion, 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: 11. 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 69/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 20 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3964 tokens
- 100Progress reporting. Reports progress
- 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 (4 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)
- +3Description length 921: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 15 headings
- +3Step-by-step instructions: 20 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.