Security audit

财务

Security checks across malware telemetry and agentic risk

Overview

This finance skill is not clearly malicious, but it asks for broad execution and file-write capability while its instructions are inconsistent and partly unrelated to finance data lookup.

Review this skill carefully before installing. It appears to be a templated finance helper rather than malware, but only use it if you are comfortable granting broad read, write, and command execution capability to instructions that do not clearly define safe finance-data boundaries. Avoid using it for trading, account actions, private financial files, or credential handling unless the publisher narrows and clarifies the behavior.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Intent-Code Divergence

Medium

Confidence: 80% confidence
Finding: The documentation presents conflicting operational boundaries: it says the skill is not for real-time trading execution, yet elsewhere advertises command execution capability. This ambiguity can cause an agent or user to overtrust the skill's scope and permit actions with system-side effects that are unnecessary for a finance lookup skill.

Intent-Code Divergence

Medium

Confidence: 92% confidence
Finding: The file simultaneously describes the skill as MD+execute() and as pure Markdown/natural-language driven, creating uncertainty about whether the agent may execute code or only provide guidance. In security-sensitive agent environments, this kind of ambiguity can bypass user expectations and policy enforcement around tool usage.

Intent-Code Divergence

High

Confidence: 97% confidence
Finding: The declared purpose is financial tracking, but the output schema is for a code/security scoring report. Such a mismatch is dangerous because it suggests the skill may be a templated or mislabeled wrapper that can induce agents to process the wrong task type, mishandle data, or activate in inappropriate contexts.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The activation guidance says to use the skill whenever the user needs finance-related functionality, which is overly broad for a skill that claims execution, file, and API capabilities. Broad triggers increase the chance the agent invokes this skill in unrelated or higher-risk financial scenarios beyond its documented competence.

Missing User Warnings

Medium

Confidence: 90% confidence
Finding: The skill advertises file writing, API integration, and command execution without clear user-facing warnings or approval gates for data modification and system impact. In agent settings, this can lead to silent external calls, filesystem changes, or shell execution under the guise of a benign finance skill.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.