Back to skill

Security audit

China Technical Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill performs disclosed technical indicator analysis for Chinese futures and does not show hidden execution, persistence, credential access, or destructive behavior.

Before installing, understand that this is a market-analysis helper, not a trading system or financial adviser. It may call public quote APIs and calculate indicators, but any buy/sell signal should be verified independently and used with risk controls.

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
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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The code substantially overlaps with the indicator-computation portion of the description: it does calculate MACD, KDJ, RSI, moving averages, and Bollinger Bands. However, the declared purpose also claims analysis for Chinese futures markets using data from china-commodity-quotes and generation of buy/sell signals and chart descriptions. In reality, this chunk is only a generic indicator library operating on input arrays, with no market-specific data access, no chart-description generation, and only limited crossover detection rather than a broader signal-generation system. Therefore the description overstates the implemented behavior in material ways.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly guides an agent to produce buy/sell recommendations for financial instruments without a prominent risk disclaimer, suitability warning, or framing as informational analysis only. In context, this can cause users to act on overstated or automated trading advice, especially when the skill presents recommendations in a decisive signal format that may appear authoritative.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill title, trigger examples, and output examples strongly assume Chinese-language interaction and terminology, but the file does not say this is optional or limited to users who want Chinese output. Under the language/locale policy, a skill should not impose a specific language without user opt-in or a clearly documented justification.

Content

No source excerpt is available for this finding.