ClawHub
Back to skill

Security audit

Aliyun Fc Agentrun

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Alibaba Cloud AgentRun management skill, but it can create and delete real cloud resources, so users must run it carefully.

Install only if you intend to manage Alibaba Cloud AgentRun resources. Use least-privileged RAM or temporary STS credentials, verify the endpoint region and runtime or endpoint IDs before running cleanup, and keep generated JSON response files private because they may contain cloud resource metadata.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill documents and relies on sensitive environment variables for cloud credentials and writes artifacts to disk, but it does not declare permissions for those capabilities. This creates a trust and review gap: operators may approve or run the skill without understanding that it can access secrets and persist potentially sensitive API responses or operational data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documented cleanup script deletes runtime resources but is presented without a prominent destructive-action warning or confirmation guidance. In an infrastructure-management skill, this increases the risk of accidental deletion of production AgentRun runtimes or endpoints, especially when users copy and run commands directly.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
This script performs irreversible deletion of a runtime endpoint and then the runtime itself immediately after reading environment variables, with no interactive confirmation, dry-run mode, safety check, or validation that the target is expected. In an operational skill that manages cloud AgentRun resources, this increases the risk of accidental or misdirected deletion if environment variables are wrong, stale, or attacker-influenced in the execution environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.