Back to skill

Security audit

Alibabacloud Governance Evaluation Report

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Alibaba Cloud Governance Center reporting tool that reads governance results and formats them, with credential and cleanup cautions but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you want an agent to query Alibaba Cloud Governance Center data for your account. Use a dedicated read-only RAM policy or temporary/role-based credentials, avoid pasting secrets into logs or shell history, review the Aliyun auto-plugin setting, and treat resource/compliance results as sensitive cloud account information.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill instructs the agent/user to execute shell commands, read local reference files, and includes a destructive cleanup command, yet it declares no explicit permissions or capability boundaries. This mismatch is dangerous because it can cause the platform or user to underestimate the skill's operational power and approve execution without proper consent or sandboxing.

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
This file substantially exceeds the stated skill purpose of governance evaluation reporting by teaching installation, authentication setup, profile management, plugin installation, and general Aliyun service usage. In an agent skill context, this expands operational capability from read/report tasks into broad cloud administration, increasing the chance the skill can be repurposed for unintended or higher-risk actions.

Context-Inappropriate Capability

Medium
Confidence
94% confidence
Finding
The sections on environment variables, multiple profiles, and credential priority enable reusable general-purpose cloud administration workflows rather than a narrowly scoped governance-report function. In a skill package, this kind of capability over-breadth can facilitate lateral use of stored credentials across projects and services beyond the intended reporting domain.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
python3 scripts/governance_query.py --refresh overview

# Clear cache manually
rm -rf ~/.governance_cache/
```

## Best Practices
Confidence
95% confidence
Finding
rm -rf ~

Tool Parameter Abuse

High
Category
Tool Misuse
Content
python3 scripts/governance_query.py --refresh overview

# Clear cache manually
rm -rf ~/.governance_cache/
```

## Best Practices
Confidence
95% confidence
Finding
rm -rf ~/.governance_cache/

VirusTotal

42/42 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.