Security audit

Quant Tools 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a quantitative finance research skill with expected market-data and backtesting capabilities, but users should treat its trading-related workflows carefully.

Install only if you intend to use quantitative finance tooling. Before using live trading, deployment, or external-data workflows, confirm the exact action, credentials, account scope, and whether the result is research-only, paper trading, or production/live trading.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger list includes broad terms such as “量化”, “quant”, “因子”, and “学术研究”, which can cause the skill to activate for loosely related user requests. In a skill that discusses trading, backtesting, data interfaces, and API/service packaging, overbroad invocation increases the chance of unintended exposure to impactful financial workflows or external-data actions.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill describes capabilities involving real trading frameworks, external financial data retrieval, API wrapping, and multi-user research environments, but does not clearly warn users about external network access, operational risk, or the consequences of trading-related actions. In this context, omission of warnings is more dangerous because users may assume these tools are purely analytical when they can support live trading, data ingestion, and deployment workflows.

Static analysis

No suspicious patterns detected.