eastmoney skills

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This skill appears to do what it says—manage a simulated stock account—but users should know it can place/cancel simulated trades, uses an API key, and saves account results locally.

Install only if you intend to connect a 妙想 simulated trading account. Configure the API key carefully, keep MX_API_URL pointed at the legitimate provider endpoint, review any buy/sell/cancel request before issuing it, and periodically clean the local output files if they contain account details.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI02: Tool Misuse and Exploitation
Low
What this means

If invoked with trade or cancel wording, the agent may change the user's simulated portfolio state.

Why it was flagged

The skill intentionally converts user wording into API calls that can submit simulated trades or cancel orders. This matches the stated simulator purpose, but it is a state-changing capability.

Skill content
根据**用户问句**自动识别意图并调用对应接口... **买入卖出操作**... **撤单操作**
Recommendation

Use clear prompts and review order details before asking it to buy, sell, sell all, or cancel orders; the skill author should add an explicit confirmation step for mutating operations.

#
ASI03: Identity and Privilege Abuse
Low
What this means

Anyone with the configured API key may be able to access or change the linked simulated trading account through the provider API.

Why it was flagged

The helper reads an API key from the environment and sends it as an authentication header to the configured API URL. This is expected for this provider integration, but it is credentialed account access.

Skill content
MX_APIKEY = os.environ.get('MX_APIKEY') ... headers = { 'apikey': MX_APIKEY, 'Content-Type': 'application/json' }
Recommendation

Only configure an API key from the legitimate provider page, keep it secret, and avoid setting MX_API_URL to an untrusted endpoint.

#
ASI06: Memory and Context Poisoning
Low
What this means

Simulated account details may remain on disk after use and could be read later by someone with access to the workspace.

Why it was flagged

The skill discloses that it saves raw API responses and text outputs locally. These files may contain simulated holdings, balances, orders, or trade history.

Skill content
默认输出目录: `/root/.openclaw/workspace/mx_data/output/` ... `mx_stock_simulator_{query}.json` - API 原始 JSON 数据
Recommendation

Treat the output directory as sensitive and delete exported JSON/text files when they are no longer needed.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

If a user manually installs dependencies, the exact requests version may vary.

Why it was flagged

The Python dependency is not version-pinned. There is no automated install spec in the artifacts, so this is mainly a reproducibility/provenance note rather than evidence of unsafe installation.

Skill content
requests
Recommendation

Pin dependency versions if this skill is packaged for automated installation.