Security audit

Ledger Monthly Report

Security checks across malware telemetry and agentic risk

Overview

This is a narrow ledger-reporting skill that runs a local monthly report script and creates CNY charts, with no evidence of hidden or unrelated behavior.

Before installing, confirm this is the ledger workspace that has projects/scripts/monthly_report_cny.py, projects/.venv-chart, and projects/data. Be aware that reports use amount_cny and default the month using Asia/Taipei time, so specify the month explicitly if that default is not right for you.

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 (2)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The skill description uses broad triggers such as 统计收支, 看占比, and 画图表 without clear boundaries tying invocation specifically to ledger data or this project’s financial dataset. That can cause over-broad activation in unrelated contexts, leading the agent to run local scripts and process potentially sensitive financial data when the user only asked for generic charts or summaries.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill hardcodes Asia/Taipei for date resolution and CNY as the reporting baseline without user opt-in or visible justification. This can silently produce incorrect reporting periods or misleading currency-normalized results for users in other locales, which is especially risky in a financial reporting skill where date and currency assumptions materially affect outputs.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal