ClawHub
Back to skill

Security audit

Statistics Skill

Security checks across malware telemetry and agentic risk

Overview

The skill performs statistics interpretation, but it sends pasted research results to Moonshot/Kimi without clear user-facing disclosure and includes an exposed API credential.

Review carefully before installing. Do not paste participant identifiers, health or student records, confidential datasets, or sensitive unpublished results unless you are comfortable sending that content to Moonshot/Kimi. The publisher should remove and rotate the embedded API key, require a user-provided credential, and add a clear external-processing notice with consent or a local-only option.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill’s stated purpose is local statistics interpretation, but it sends user-supplied statistical results to a third-party LLM service for processing. Statistical output can contain unpublished research data, health-study results, or other sensitive information, and the code provides no clear disclosure, minimization, or consent before exfiltrating that content.

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
A live API key is hardcoded directly in the script, which exposes the credential to anyone with file access and enables unauthorized API usage, billing abuse, or service impersonation. Embedding secrets in source code is a well-known security failure and is especially risky if the skill is shared, committed, or deployed broadly.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script transmits user-provided statistical content to an external API without any explicit privacy notice or confirmation. In research and academic contexts, those inputs may contain confidential study results, proprietary analyses, or regulated data, making silent transmission a meaningful privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.