ClawHub
Back to skill

Security audit

Alibaba Cloud AI Content Aicontent

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Alibaba Cloud AIContent helper that uses cloud credentials, network API calls, and local output files in ways that match its stated purpose.

Install this only if you want an agent to help operate Alibaba Cloud AIContent resources. Use least-privilege Alibaba Cloud credentials, review any create/update/modify action before it runs, and treat files under output/aliyun-aicontent-generate/ as potentially containing operational metadata or API response details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill instructs use of environment credentials, networked OpenAPI access, and local file output, but it declares no permissions. That creates a transparency and governance gap: a caller or platform may invoke the skill without realizing it can read secrets from the environment, contact external services, and write artifacts to disk.

Missing User Warnings

Low
Confidence
78% confidence
Finding
The skill documents writing responses and generated artifacts to disk, but it does not clearly warn users at invocation time that local files will be created. Unanticipated file creation can expose sensitive API responses, operational metadata, or identifiers to other local users/processes and can surprise operators in restricted environments.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.