ClawHub

Analyse Data

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent ChartGen cloud integration that asks for confirmation before sending selected prompts and spreadsheet files for analysis.

Install only if you are comfortable using ChartGen as an external cloud processor. Review each confirmation prompt carefully, avoid uploading spreadsheets with data you cannot share with ChartGen, and prefer a dedicated ChartGen API key.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill declares use of an environment variable (`CHARTGEN_API_KEY`) but does not declare corresponding permissions, creating a mismatch between documented capabilities and enforceable policy. This weakens review and runtime governance because the skill can rely on sensitive configuration without transparent permission scoping.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The invocation description is extremely broad, covering generic visualization, analysis, reporting, spreadsheet uploads, and even simple mention-based triggers. This can cause the skill to activate for many unrelated or sensitive data tasks, increasing the chance that user data is routed to the external ChartGen service without sufficiently specific user intent.

Missing User Warnings

High
Confidence
98% confidence
Finding
The skill encourages uploading Excel/CSV files and sending them to an external API, but it does not clearly disclose to the user that their local data will leave the host environment and be transmitted to ChartGen. This is especially risky because spreadsheets often contain sensitive business, financial, or personal data, and the workflow normalizes multi-file upload and external-source analysis.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The tool uploads user-specified local files to a remote ChartGen API as part of normal operation, but the code itself provides no explicit warning, consent gate, or policy check before transmission. In a skill environment, this increases the risk of unintended disclosure of sensitive spreadsheet contents, especially when agents may select files automatically or users may not realize files leave the local environment.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
- With files: "ChartGen is analyzing your data, ~2–5 min..."
- PPT: "ChartGen is generating your PPT, ~10–20 min, please be patient..."

**Then call the tool:**
```
node tools/chartgen_api.js submit "<query>" <channel> [files...]
```
Confidence
90% confidence
Finding
tool:*

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal