Security audit

tqsdk-query

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Tianqin/TQSDK market-data reader, with credential and dependency cautions but no evidence of hidden, destructive, or unrelated behavior.

Install this only if you are comfortable providing a Tianqin/TQSDK username and password as environment variables. Prefer credentials limited to market-data access, keep those variables scoped to this skill, and consider pinning dependency versions for reproducible deployments. Also verify or remove the missing tqsdk_client import before relying on the skill, because it may prevent the package from loading.

SkillSpector

Vulnerability Patterns

Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill documentation explicitly requires secrets in environment variables (`TQ_USERNAME`, `TQ_PASSWORD`) while declaring no permissions, creating a mismatch between documented behavior and declared security boundaries. This can lead to overbroad or implicit secret access, reduced user visibility into what sensitive data the skill needs, and weaker review/auditing of credential handling.

Unpinned Dependencies

Low

Category: Supply Chain
Content: tqsdk>=3.0.0 pandas>=1.3.0
Confidence: 93% confidence
Finding: The dependency specification `tqsdk>=3.0.0` is unpinned, so future installs may resolve to different versions with behavioral changes or newly introduced vulnerabilities. This weakens build reproducibility and increases supply-chain risk, especially for a skill that retrieves market data and may run in automated trading environments.

Unpinned Dependencies

Low

Category: Supply Chain
Content: tqsdk>=3.0.0 pandas>=1.3.0
Confidence: 97% confidence
Finding: The dependency specification `pandas>=1.3.0` is unpinned, allowing installation of arbitrary newer versions that may introduce security issues, breaking changes, or inconsistent behavior across environments. In data-processing skills, this can affect both reliability and exposure to dependency supply-chain problems.

Static analysis

No suspicious patterns detected.