edgeone skill scanner

Files (1)

• SKILL.md

SKILL.md (first lines)

# Tencent Zhuque Skill Scanner

Agent Skills security scanner powered by Tencent Zhuque Lab A.I.G.
Compatible with any agent platform that supports skills (e.g. OpenClaw, Qclaw, WorkBuddy, CodeBuddy, Cursor, Windsurf, Claude Code, etc.).

## Security Declaration

**Local-only analysis**: this scanner performs static analysis by reading skill files only.
No file contents, credentials, or personal data are sent externally.

---

## Language Detection Rule — EXECUTE BEFORE ANYTHING ELSE

Detect the language of the user's triggering message and lock the output language for the entire run.
This detection is an **internal step only** — do NOT output any text that reveals the detection
result, such as "当前输出语言为中文", "Detected language: English", or similar meta-statements.
Simply use the detected language silently for all subsequent output.

| User message language | Output language |
|-----------------------|-----------------|
| Chinese | Chinese — entire output in Chinese |
| English | English — entire output in English |
| Other language | Match that language |
| Cannot determine | Default to Chinese |

All output — scan start prompt, table headers, labels, prose, verdict, and footer — must be written
exclusively in the detected language. Do NOT mix languages or announce the language choice at any point.

---

## Scan Start Prompt

Before starting the scan, output the following line with `{skill}` replaced by the actual skill name.
Translate it to match the detected output language.

`🔍 腾讯朱雀实验室 A.I.G Skill Scanner 正在检测 {skill} 的安全性，请稍候...`

---

## Scan Workflow

Determine which mode to use based on the user's request:

| User intent | Mode |
|-------------|------|
| Scan **all** skills on a platform, or asks "are my skills safe?" without specifying a file | **Mode A — Full-platform scan** |
| Scan a **specific** skill file or a named skill | **Mode B — Single-skill audit** |

---

### Mode A — Full-platform scan

Use this mode when the user wants to check the security of all skills on a given agent platform.

#### A-1. Identify the platform

Determine which agent platform the user is referring to. Common platforms include but are not
limited to: **OpenClaw, Cursor, Windsurf, CodeBuddy, WorkBuddy, Claude Code, qclaw**, etc.

How to determine:
- If the user explicitly names a platform, use that.
- If the user says "scan my skills" or "check all skills" without naming a platform, infer the
  platform from the current runtime environment (e.g. if running inside CodeBuddy, the platform
  is CodeBuddy).
- If the platform still cannot be determined, ask the user to clarify.

#### A-2. Discover skills

Once the platform is identified, use the platform-specific method below to enumerate all installed
skills. Do **NOT** output a list of all discovered skill names and paths before scanning — proceed
directly to auditing each skill one by one.

**CRITICAL — No skill may be skipped**: Both user-installed skills and system/platform built-in
skills must be included. If a platform ships pre-installed or bundled skills, they must be
discovered and audited with the same rules as user-installed ones.

**Platform-specific skill discovery methods:**

| Platform | Discovery method |
|----------|-----------------|
| **OpenClaw** | Ask the Agent: "你的 skill 有哪些" or "list your skills" to get the full skill list |
| **CodeBuddy** | Scan **both** the system directory `~/.codebuddy/plugins/marketplaces/` and the user directory `~/.codebuddy/plugins/` for all skill files and subdirectories. Also check if the platform exposes a built-in skill list via its tools (e.g. `use_skill` tool's `<available_skills>` section) and include those. |
| **Cursor** | Scan the local directory `~/.cursor/extensions/` and project-level `.cursor/skills/` for skill definitions |
| **Windsurf** | Scan the local directory `~/.windsurf/skills/` and project-level `.windsurf/skills/` for skill files |
| **Claude Code** | Scan project-level `.claude/skills/` directory and check `~/.claude/skills/` for global skills |
| **qclaw** | Ask the Agent: "你的 skill 有哪些" or "list your skills" to get the full skill list |
| **WorkBuddy** | Ask the Agent: "你的 skill 有哪些" or "list your skills" to get the full skill list |
| **Other / Unknown** | Ask the Agent for its skill list |

> **Note**: The paths above are common defaults and may vary by version or user configuration.
> If the expected directory does not exist or is empty, fall back to asking the Agent or asking the
> user for the correct skill storage location.

#### A-3. Audit each skill

For each discovered skill, perform the local audit described in the **Local Audit** section below.
Output a separate report card for each skill, then a final summary at the end.

---

### Mode B — Single-skill audit

Use this mode when the user specifies a particular skill file or skill name.

- Locate the skill file (by path, name, or search).
- Proceed directly to the **Local Audit** section below.

---

### Local Audit

#### 1. Skill information collection

Output a short inventory with only the minimum context needed for audit:

- Skill name and one-line claimed purpose from `SKILL.md`
- Files that can execute logic: `scripts/`, shell files, package manifests, config files
- Actual capabilities used by code: file read/write/delete, network access, shell or subprocess

From Tencent/AI-Infra-Guard, MIT.

More from Tencent/AI-Infra-Guard