ClawHub

Journal Deep Intel Extractor

Security checks across malware telemetry and agentic risk

Overview

This skill appears to fetch PubMed article metadata and abstracts as advertised, then save the results locally as JSON.

Before installing, confirm you are comfortable with the skill contacting PubMed and saving article abstracts under ~/Documents/Journal_Intel. Pin and maintain the Python dependencies in your environment if reproducibility or parser/client security matters, and periodically delete archived JSON files if the research topics are sensitive on a shared machine.

SkillSpector

By NVIDIA
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 (7)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares no permissions, yet its entrypoint and description indicate it performs network access and writes files locally. This creates a transparency and policy-enforcement gap: users or hosting systems may approve the skill without understanding that it can exfiltrate data over the network or persist data on disk.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill documentation mentions local archival to ~/Documents/Journal_Intel/, but does not present it as a clear warning or consent-relevant behavior. Silent or easy-to-miss local writes can expose sensitive research activity, consume disk space, or leave residual data on shared machines.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
beautifulsoup4
lxml
Confidence
96% confidence
Finding
requests

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
beautifulsoup4
lxml
Confidence
93% confidence
Finding
beautifulsoup4

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests
beautifulsoup4
lxml
Confidence
97% confidence
Finding
lxml

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); 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) +7 more

High
Category
Supply Chain
Confidence
98% confidence
Finding
requests

Known Vulnerable Dependency: lxml — 10 advisory(ies): CVE-2021-43818 (lxml's HTML Cleaner allows crafted and SVG embedded scripts to pass through); CVE-2014-3146 (lxml Cross-site Scripting Via Control Characters); CVE-2021-28957 (lxml vulnerable to Cross-Site Scripting ) +7 more

High
Category
Supply Chain
Confidence
97% confidence
Finding
lxml

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal