customer-segment-eng

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This skill appears to do legitimate customer segmentation, but it automatically processes sensitive banking customer data and writes customer-level results without enough user control or privacy safeguards.

Install only for controlled customer-segmentation work on datasets you are authorized to process. Confirm before running it on any uploaded banking data, use a restricted output directory, remove or pseudonymize customer IDs where possible, and avoid saving customer-level exports unless they are necessary.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Ambiguous natural-language triggers increase the chance that the skill runs when the user meant a different type of analysis or only wanted basic inspection of uploaded data. Because the skill handles bank customer data and performs profiling/segmentation automatically, accidental invocation can expose sensitive attributes in outputs and produce unintended downstream files.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: Ambiguous natural-language triggers increase the chance that the skill runs when the user meant a different type of analysis or only wanted basic inspection of uploaded data. Because the skill handles bank customer data and performs profiling/segmentation automatically, accidental invocation can expose sensitive attributes in outputs and produce unintended downstream files.

Missing User Warnings

Low

• Confidence: 87% confidence
• Finding: The skill specifies automatic creation of CSV, PNG, and Markdown output files but does not indicate that users will be warned before files are written. In this context, generated artifacts may contain customer IDs, cluster assignments, and summary statistics, which can surprise users and increase the risk of unintended persistence of sensitive financial analysis results.

VirusTotal

65/65 vendors flagged this skill as clean.