Back to skill

Security audit

Geoskill: China Weather Data

Security checks across malware telemetry and agentic risk

Overview

This appears to be a normal weather-data tool, but users should review its privacy and dependency caveats before installing.

Install only if you are comfortable sending weather locations or place names to external services, storing a data.cma.cn API key in a local plaintext config file, and writing downloaded/QA files to paths you choose. Prefer pinned, updated dependencies and encrypted provider endpoints where possible.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Intent-Code Divergence

Medium
Confidence
92% confidence
Finding
The privacy notice states that only coordinates and date ranges are sent externally, but the code may send arbitrary user-supplied city or place names to external geocoding services via resolve_coordinates() and list-stations --place resolution. This can disclose sensitive location queries or user-entered place names contrary to the stated privacy guarantee, increasing privacy and trust risk.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The skill explicitly documents configuring an API key, downloading output files, and calling external weather services, but it does not clearly disclose the privacy and local side effects to users at the point of use. This can lead users to unknowingly transmit location/query data and credentials to third-party services or write files to disk without informed consent.

External Transmission

Medium
Category
Data Exfiltration
Content
## Data Sources

- **Primary**: [中国气象数据网](http://data.cma.cn/) — Official China meteorological data
- **Fallback**: [Open-Meteo](https://open-meteo.com/) — Free, no key required

---
Confidence
95% confidence
Finding
http://data.cma.cn/

External Transmission

Medium
Category
Data Exfiltration
Content
## 数据来源

- **主源**: [中国气象数据网](http://data.cma.cn/) — 中国官方气象数据
- **备源**: [Open-Meteo](https://open-meteo.com/) — 免费,无需密钥
Confidence
95% confidence
Finding
http://data.cma.cn/

Session Persistence

Medium
Category
Rogue Agent
Content
def write_qa_summary(qa_path, *, skill, command, args, payload, extra=None):
    """Write a JSON run-summary sidecar to qa_path (Phase 5 optimization).

    The sidecar includes the request params (place/city, date range, type),
    the resolved lat/lon, the output path and a UTC timestamp so QA can
Confidence
88% confidence
Finding
Write a JSON run-summary sidecar to qa_path (Phase 5 optimization). The sidecar includes the request params (place/city, date range, type), the resolved lat/lon, the output path and a UTC tim

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
tqdm>=4.64.0
Confidence
95% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
tqdm>=4.64.0
Confidence
91% confidence
Finding
tqdm>=4.64.0

Known Vulnerable Dependency: requests==2.28.0 — 8 advisory(ies): CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High
Category
Supply Chain
Confidence
97% confidence
Finding
requests==2.28.0

Known Vulnerable Dependency: tqdm==4.64.0 — 2 advisory(ies): CVE-2024-34062 (tqdm CLI arguments injection attack); CVE-2024-34062 (tqdm CLI arguments injection attack)

Low
Category
Supply Chain
Confidence
89% confidence
Finding
tqdm==4.64.0

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.