Alicloud Ai Contactcenter Ai

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Alibaba Cloud ContactCenterAI helper with expected cloud-management permissions and no evidence of hidden or malicious behavior.

Install this only if you intend to manage Alibaba Cloud ContactCenterAI resources. Use least-privilege Alibaba Cloud credentials, verify region and resource IDs before any create/update/modify/set action, and avoid saving secrets in output artifacts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill uses sensitive capabilities (environment access for cloud credentials, network access to Alibaba Cloud endpoints, and local file writes) but does not declare permissions. This creates a transparency and governance gap: operators may invoke the skill without realizing it can read credentials, contact external services, and persist data locally, which increases the risk of unintended credential use, unauthorized API activity, or leakage of API responses into artifacts.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The description is broad enough to trigger on many ordinary cloud-management requests, increasing the chance the skill is selected in contexts where credentialed network actions and configuration changes are unnecessary or unsafe. In a cloud-management skill with access to environment credentials and the ability to perform lifecycle operations, overbroad routing meaningfully raises the risk of unintended invocation and accidental changes to production resources.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal