Bank Policy Query

• Outcome: Review
• Latest audit: May 28, 2026, 10:29 AM
• Version:
  1.0.1

Overview

The skill is coherent for bank policy lookup, but it directly exposes and reads a Feishu policy spreadsheet that appears to contain internal business fields.

Review before installing. Confirm that the referenced Feishu sheet and internal columns are intended to be accessible to all users or agents using this skill, and consider replacing the raw sheet identifiers with a scoped backend data source or redacting internal-only fields.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger criteria are broad and effectively mandate use of the skill whenever bank-policy terms appear with a city or region name. That can cause over-invocation and unintended retrieval of internal policy data in contexts where the user did not explicitly request access to bank subsidy policy details, increasing the chance of unnecessary data exposure and misleading answers from the wrong skill.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill exposes a concrete Feishu spreadsheet URL, token, sheet identifier, schema, and notes that include internal-only fields such as '内部备注'. Even if credentials are not shown, publishing direct resource identifiers and internal data structure materially lowers the barrier to unauthorized discovery, scraping, prompt-targeted exfiltration, or accidental leakage of sensitive business policy information.

VirusTotal

64/64 vendors flagged this skill as clean.