AB alibabacloud-aisc-skill-inspection
Submit Alibaba Cloud AISC Skill file security scans, poll scan tasks, diagnose API or upload failures, and interpret scan reports for malicious code, prompt injection, hardcoded credentials, sensitive data, risky configuration, and other Skill package security findings. Use when the user asks whether a Skill package or Skill file is safe, wants to scan/check/detect a Skill package, provides one or more Skill download URLs for AISC security detection, asks to run or poll CreateSkillFileCheck/ListSubTasks, asks about check-report.json or rootTaskId status, needs help with permission/parameter/throttling/system scan errors, or needs to choose between multiple candidate Skill files for security scanning. Trigger phrases include AISC scan, Skill security check, Skill file check, Skill 安全检测, Skill 文件安全扫描, 扫描 Skill 包, 检测 Skill 是否安全, and 检查 Skill 文件有没有恶意代码/敏感凭据/prompt 注入.
Submit Alibaba Cloud AISC Skill file security scans, poll scan tasks, diagnose API or upload failures, and interpret scan reports for malicious code, prompt…
As a process B 77/100 · Nearly there — weak spots: result and completion
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 · 0
✓ No critical or high findings
Files scanned: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5484 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 77/100
- 0Result and completion. Does not say what the result is
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Execution cost. Instruction body is 5484 tokens
- 100Steps. 81 steps
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 15 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
- low 14 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
- +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 876: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 18 headings
- +3Step-by-step instructions: 81 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.