Industry Research Agent

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate report-generation skill, but it will run a local Python script, use your Eastmoney API key, send the industry topic to Eastmoney, and save report files.

This skill looks coherent for generating industry reports. Before installing, make sure you trust the Eastmoney API integration, configure EM_API_KEY only in a trusted environment, choose an appropriate local output directory for generated PDF/DOCX files, and avoid including confidential details in the industry topic unless you are comfortable sending them to the external service.

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.

#
ASI03: Identity and Privilege Abuse
Low
What this means

Installing and using the skill requires granting it access to an Eastmoney API credential.

Why it was flagged

The script requires an API key and sends it as an authentication header to the Eastmoney service. This is expected for the stated purpose, but it is still sensitive credential use.

Skill content
EM_API_KEY = os.environ.get("EM_API_KEY", "") ... headers={"Content-Type": "application/json", "em_api_key": EM_API_KEY}
Recommendation

Use a dedicated, least-privileged API key if available, keep it in environment variables only, and do not paste it into chats or logs.

#
ASI05: Unexpected Code Execution
Low
What this means

The skill will run local Python code when generating a report.

Why it was flagged

The skill instructs the agent to run the included Python script with a model-extracted topic. This is central to the skill and not hidden, but users should know local code will execute.

Skill content
python3 {baseDir}/scripts/get_data.py --query "{{topic}}"
Recommendation

Install only if you are comfortable running the included script and have reviewed the configured output location.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

A future install may receive whatever httpx version is current in the package index.

Why it was flagged

The skill documents installation of the httpx dependency without a pinned version. This is a normal dependency for HTTP API access, but unpinned packages have weaker reproducibility.

Skill content
"package": "httpx" ... pip3 install httpx --user
Recommendation

If reproducibility matters, pin and review dependency versions in your environment.

#
ASI07: Insecure Inter-Agent Communication
Low
What this means

The industry topic you ask about is sent to Eastmoney, and the generated report may include a service-provided sharing link.

Why it was flagged

The script sends the user-derived industry query to a fixed external Eastmoney service and returns a share_url. This is disclosed and purpose-aligned, but it is an external data flow.

Skill content
MCP_URL = "https://ai-saas.eastmoney.com/proxy/app-robo-advisor-api/assistant/write/industry/research" ... client.post(MCP_URL, json={"query": query}, headers={...})
Recommendation

Avoid putting confidential business details into the topic unless you are comfortable sending them to the Eastmoney service, and verify any returned share link before opening or forwarding it.