Security audit

T Trading

Security checks for vulnerabilities and agentic risk

Overview

This is a pure Markdown trading-analysis prompt skill with no code execution, persistence, credential access, or hidden data flow, but users should treat its market outputs cautiously.

Install only if you want a Chinese-language technical trading-analysis prompt. Ensure your agent activates it only for explicit market-analysis requests, verify any live market data independently, and do not treat its entry, stop-loss, take-profit, or position-sizing outputs as personalized financial advice or permission to trade automatically.

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
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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The natural-language activation text says the skill can be triggered directly through ordinary conversation, but it does not define clear boundaries for when the framework should or should not take control. In an agent environment, ambiguous invocation increases the risk of prompt-routing errors, where unrelated or exploratory user queries are interpreted as requests for actionable trading analysis.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keyword list is broad enough to match ordinary finance questions such as support/resistance, EMA, Fibonacci, or short-term trading. In a prompt-based skill system, this can cause unintended activation, making the assistant follow this trading framework when the user only wanted general discussion, which can override user intent and produce unsolicited trading instructions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The skill is written to operate in Chinese and requires a fixed report format without offering language negotiation or documenting a justified locale restriction. This can cause user misunderstanding, misexecution of financial instructions, or inaccessible risk disclosures when the user interacts in another language, which is especially problematic in a trading-advice context where clarity matters.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation conditions are broad enough to match common trading-related phrases, stock tickers, and generic intent questions, which can cause the skill to trigger when the user did not explicitly request this specific strategy. In a prompt-routing system, that can override user intent, inject unsolicited financial guidance, and increase the chance of inappropriate or unsafe investment recommendations being produced.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger conditions are broad enough that ordinary mentions of stock tickers, crypto symbols, or generic short-term trading intents can activate the skill unexpectedly. In a prompt-routing system, this can cause unintended takeover of conversations, leading the agent to produce domain-specific trading guidance when the user did not explicitly ask for this framework.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill mandates a fixed Chinese output template without checking the user's language preference. This can degrade usability and cause miscommunication, especially in financial contexts where misunderstanding entry, stop-loss, or risk instructions may lead to user harm.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.