AC alibabacloud-sas-vul-repair
Alicloud Service Scenario-Based Skill. Use for the vulnerability module of Alibaba Cloud Security Center (SAS): querying and filtering vulnerabilities (by severity/type/asset/status), triggering vulnerability repair and post-fix re-verification, interpreting repair failure error codes (8009, 8037, 9003, etc.) with repository and network troubleshooting, handling "fixed but still detected" status refresh, and manual repair guidance for non-standard systems (self-compiled kernels, non-Alibaba-Cloud hosts, offline environments, custom images, EOL systems). Triggers: "Security Center vulnerability", "vulnerability repair", "vulnerability fix", "fix failed", "repair failed", "vulnerability error code", "fixed but still detected", "re-verify vulnerability", "unfixed vulnerability list", "self-compiled kernel", "manual vulnerability fix", "CVE", "漏洞修复", "修复失败", "漏洞错误码", "已修复仍检出", "重新验证漏洞", "漏洞复检", "未修复漏洞清单", "yum 源超时", "自编译内核", "手动修复漏洞".
Alicloud Service Scenario-Based Skill.
As a process C 63/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
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 Risky intent
intent-offensive-securityreferences/api-reference.md:432Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| SearchTags | string | No | Filter by tag: reboot required, remote exploit, EXP exists, exploitable, local privilege escalation, code execution |
-
low Dangerous commands
cmd-privilegereferences/cli-installation-guide.md:37Privilege 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:43Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv aliyun /usr/local/bin/
security skill
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6935 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 63/100
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 16 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Steps. 33 steps, 7 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6935 tokens
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 944: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Structure: 27 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.