ClawHub
Back to skill

Security audit

Alibabacloud Ddos Native Intercept Query

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Alibaba Cloud DDoS troubleshooting skill, but it needs review because it changes local Aliyun CLI and plugin settings while presenting the workflow as read-only.

Install only if you are comfortable letting the skill alter local Aliyun CLI/plugin configuration and query DDoS protection metadata through the selected Alibaba Cloud profile. Use a least-privilege RAM role or temporary STS credentials, review plugin updates separately where possible, and check whether auto-plugin-install and AI-mode remain enabled after use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The skill asserts it is strictly read-only, yet it directs execution of `aliyun configure set --auto-plugin-install true` and later AI-mode toggles that modify local CLI configuration. This creates a trust and side-effect mismatch: users may authorize the skill expecting no state changes, but it persists configuration changes that can alter future command behavior or plugin installation policy.

Context-Inappropriate Capability

Medium
Confidence
87% confidence
Finding
The skill includes installation, plugin update, and environment mutation steps that exceed its declared purpose of querying intercept records. Broad setup powers increase the blast radius of a support workflow and create unnecessary supply-chain and operational risk, especially when updates or installs are triggered in the same trust context as incident analysis.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.