AISC Skill File Security Check

Help users submit Skill archives to Alibaba Cloud Agent Security Center (AISC) for security scanning, poll detection tasks, and explain the returned results.

Use this Skill broadly for Skill security detection. If the user asks whether a Skill package is safe, whether it contains malicious code, prompt injection, hardcoded credentials, sensitive data, or risky configuration, or asks how to run, poll, diagnose, or interpret an AISC Skill scan, use this Skill.

Natural Language Activation

Use this Skill for an explicit or implicit Skill security request; the user does not need to name AISC, this Skill, or the Python script. Load SKILL.md before deciding which inputs are missing or asking a follow-up. Selecting/loading the Skill is separate from submitting a cloud request.

• A clear safety question such as “这个 Skill 安不安全”, “能放心安装吗”, or “有没有恶意代码/敏感凭据/提示词注入” activates this Skill.
• With a clear target and download URL, run the official wrapper directly; do not ask the user to repeat authorization or supply optional file names.
• With a missing URL, missing task ID, unclear AISC operation, or unselected candidates, load this Skill first, ask for only the missing input, and wait before any cloud call.
• Generic Skill writing, installation, documentation, and “处理一下 Skill” without a security intent are outside this Skill's scope.

Critical Operating Rules

These rules have highest priority for every AISC Skill file scan: