ClawHub

Zyt video compose

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chanjing video-generation helper that uses local Chanjing API credentials and uploads user-selected media, with no artifact-backed evidence of hidden or malicious behavior.

Install only if you trust Chanjing and this publisher with your Chanjing API credentials and any media you choose to upload. Use a dedicated or revocable API key if possible, protect the credentials file, review any missing helper scripts before running them, and only download or upload files when you explicitly intend to.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill describes and relies on capabilities including environment-variable access, local file read/write, and outbound network calls, but does not declare any permissions or trust boundaries. That mismatch is dangerous because users and orchestration systems cannot accurately assess what the skill can access before execution, especially since it reads credentials from disk and can write downloaded media locally.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The instruction to default to 'young, energetic' public avatars without user opt-in introduces an unjustified demographic preference into automated selection. This is risky because it can systematically bias outputs, override user intent, and produce inappropriate or discriminatory persona choices in sensitive contexts such as education, healthcare, or enterprise communications.

Credential Access

High
Category
Privilege Escalation
Content
本 Skill 使用：

* 配置文件：`~/.chanjing/credentials.json`
* 若设置环境变量 `CHANJING_CONFIG_DIR`：使用 `$CHANJING_CONFIG_DIR/credentials.json`
* API 基础地址固定：`https://open-api.chanjing.cc`
Confidence
97% confidence
Finding
credentials.json

Credential Access

High
Category
Privilege Escalation
Content
本 Skill 使用：

* 配置文件：`~/.chanjing/credentials.json`
* 若设置环境变量 `CHANJING_CONFIG_DIR`：使用 `$CHANJING_CONFIG_DIR/credentials.json`
* API 基础地址固定：`https://open-api.chanjing.cc`

当本地缺少 AK/SK 或 AK/SK 无效时，脚本默认返回登录引导信息，不自动打开浏览器。
Confidence
96% confidence
Finding
credentials.json

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal