AB alibabacloud-waf-rule-effectiveness-check
Diagnose why a configured Alibaba Cloud WAF 3.0 custom protection rule (custom ACL, CC / rate limiting, scan protection, IP blacklist) is not working: name the first broken link in the chain and hand back the console fix path. Read-only checks of configuration state only; never sends test traffic. Use it when a customer says a rule has no effect at all, a rule matches in the logs but nothing is blocked, an attack that should have been blocked got through, a rule worked yesterday but not today, or a CC or rate-limiting rule does not trigger or bans far too widely. Not for: explaining why one specific request was blocked or looking it up by trace_id, whitelist rule effectiveness itself, live attack sample validation, built-in rule toggles, config export, or reports. Triggers: "规则不生效", "规则配了但不生效", "自定义规则不生效", "预期拦未拦", "该拦的没拦住", "漏拦截", "规则命中但没拦", "规则昨天还好今天失效", "CC不触发", "误封面过大", "规则为什么没生效", "WAF rule not effective", "rule not taking effect", "rule hit but not blocked"
Diagnose why a configured Alibaba Cloud WAF 3.0 custom protection rule (custom ACL, CC / rate limiting, scan protection, IP blacklist) is not working: name…
As a process B 74/100 · Nearly there — weak spots: result and completion, execution cost
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 · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:19Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv aliyun /usr/local/bin/
security skill -
low Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:27Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv aliyun /usr/local/bin/
security skill
A further 1 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8040 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 74/100
- 40Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 8040 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 85Steps. 47 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 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
- low 17 top-level sections: this looks like several domains in one skill
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
- +3Description length 977: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 9 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 26 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (9 of 9)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.