Security audit

Market Alert

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown instruction file, but it expands from stock alerts into sensitive personal finance records and advice without clear limits.

Review before installing if you only want stock alerts. The skill has no code-level malicious behavior, but its instructions invite handling sensitive account records, statements, tax details, bills, and allocation advice without clear consent boundaries or data-handling limits.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill manifest presents a stock-alert capability, but the body of the documentation describes much broader personal finance and portfolio functions, including asset totals, transaction records, statements, tax details, and asset-allocation advice. This scope mismatch can cause an agent to invoke the skill for sensitive financial tasks outside its intended purpose, increasing the risk of over-collection of personal financial data and unauthorized task routing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example trigger phrases are generic templates such as asking how to use the skill for a 'specific scenario task' or asking for 'latest玩法/优惠信息,' which are not tightly bound to stock-alert functions. Overbroad triggers can cause the system to match ordinary user requests unrelated to market alerts, leading to unintended invocation and possible exposure of financial-context capabilities beyond the user’s intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The natural-language content presents the skill entirely in Chinese, and the file does not state that the skill is region-specific or that users may choose another language. This can violate language/locale policy when a specific language is imposed without opt-in or justification.
Content: No source excerpt is available for this finding.