ClawHub
Back to skill

Security audit

ask-data

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims: read a user-approved Excel file locally and answer data questions, without evidence of hidden upload, credential use, or file modification.

Install only if you are comfortable letting the agent read the Excel files you select. Avoid using it on spreadsheets with unnecessary sensitive data, confirm file paths carefully, and make sure your local Python environment has the needed data-analysis packages available.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
83% confidence
Finding
The activation examples include the generic phrase “查询数据”, which is broad enough to match many ordinary user requests and can cause this skill to trigger outside its intended scope. Over-broad activation increases the chance that the agent will request file paths or attempt local file access in contexts where the user did not explicitly intend to use this Excel-query skill, creating unnecessary exposure to local data and confusing task routing.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.