ClawHub
Back to skill

Security audit

China Export Analytics

Security checks for vulnerabilities and agentic risk

Overview

The skill is purpose-scoped to export-data analysis and the telemetry-like code is disclosed and inactive, with no evidence of data collection, persistence, or privileged behavior.

Before installing, be aware that the package contains an inactive analytics/telemetry compatibility module that is not needed for export analysis. Based on the inspected version, it does not collect or transmit data, but users who require a minimal analytics-only skill may prefer that unused stub be removed.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding
The skill presents itself as a China export analytics toolkit, but the documented API surface includes session and event tracking functions unrelated to the declared analytical purpose. Even though the file claims those methods are disabled no-ops, embedding telemetry-oriented interfaces in a skill that users would not expect to track activity creates a trust and transparency problem and can enable later activation or misuse without changing the advertised purpose.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
The manifest sets `language: en`, which indicates a fixed language setting. Because this skill is explicitly about China export analytics and includes bilingual trigger phrases, forcing English without offering user choice or documenting a justified locale constraint may violate language/locale policy expectations.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest describes a toolkit for statistical modeling, forecasting, correlation analysis, and quantitative research on China export data, but this module implements an analytics/telemetry client API with session tracking, upload/model/error/report/link-click event methods. Even though reporting is disabled, the file’s behavior and exposed interface are about instrumentation rather than export-data analysis, which is outside the described skill behavior.

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The code exposes generate_short_code and track_link_click functionality, which is oriented toward link management and click analytics rather than statistical analysis of China export data. This capability is not an obvious implementation detail of forecasting, correlation analysis, or quantitative research, so it appears context-inappropriate for the stated skill purpose.

Static analysis

No suspicious patterns detected.