ClawHub
Back to skill

Security audit

数据分析理调

Security checks for vulnerabilities and agentic risk

Overview

The skill is a data-analysis guidance document, but it declares broad command and file-writing privileges that the document itself says are not needed.

Review this skill before installing. Its data-analysis guidance is coherent, but its declared exec and write permissions are broader than the documented purpose requires; install only if you are comfortable granting command execution and file modification authority, or ask the publisher to remove or tightly justify those tools.

SkillSpector

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)

Intent-Code Divergence

Medium
Confidence
94% confidence
Finding
The skill documentation states it is a pure Markdown skill that does not require exec capability, yet the manifest declares exec in the tools list. This mismatch can mislead reviewers and users about the real privileges granted to the skill, increasing the chance that unnecessary command execution capability is approved and later abused.

Context-Inappropriate Capability

Medium
Confidence
92% confidence
Finding
The skill is presented as a data-analysis methodology framework, but it requests write and exec capabilities without a clear functional need. Excessive privileges violate least-privilege principles and create avoidable risk of file modification or command execution if the skill is invoked in an unsafe workflow.

Static analysis

No suspicious patterns detected.