Security audit

StockIndexMonitor

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language stock alert skill with no bundled executable code, credentials use, hidden execution, or destructive behavior, though its run commands reference scripts not included in the reviewed package.

Install only if you want a Chinese-market stock alert workflow and understand the red-up/green-down convention. Treat any investment suggestions as informational, not professional financial advice. Because the reviewed package does not include the referenced control.sh script, do not run a script from that path unless you separately inspect and trust it.

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

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
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The file presents the skill entirely in Chinese and explicitly states it follows Chinese investor conventions, including the red-up/green-down color scheme. Under the policy rule, forcing a specific language or locale is a violation unless the skill offers a user choice or clearly documents a justified region-specific constraint; this file does not provide such opt-in or limitation language.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest describes a stock monitoring and alerting system focused on seven technical/price-based warning rules. However, the heading at L006 broadens the skill into an 'intelligent investment advisory system,' and the changelog later mentions '新闻舆情分析', which goes beyond simple monitoring/alerting and implies advisory or analysis capabilities not reflected in the rest of the documented behavior.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file's examples, configuration, and feature list consistently describe seven alert rules based on price, volume, and technical indicators. The changelog entry claiming 'v2.0 Pro版: 新闻舆情分析' contradicts that documented behavior by asserting an additional capability that is not otherwise represented here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.