ClawHub
Back to skill

Security audit

Biomedical Literature Search

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward biomedical literature search helper that uses disclosed PubMed and bioRxiv API requests.

Install only if you are comfortable with biomedical search terms, dates, and category filters being sent to PubMed/NCBI and bioRxiv. Avoid confidential project names, unpublished research strategy, or sensitive medical details in queries unless external disclosure is acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill demonstrates live network access to PubMed and bioRxiv but does not declare any permissions or capability boundaries. This creates a transparency and governance problem: callers may invoke a skill that can send user-provided queries to external services without an explicit permission model or user awareness.

External Transmission

Medium
Category
Data Exfiltration
Content
import requests

# Fetch papers by date range
url = "https://api.biorxiv.org/details/biorxiv/2026-02-01/2026-03-01"
response = requests.get(url)
papers = response.json()["collection"]
Confidence
81% confidence
Finding
This code sends data to an external third-party endpoint (bioRxiv) over the network. In context this is the intended function of a literature-search skill, so it is not inherently malicious, but it still poses a privacy risk because user queries, research interests, or timing metadata may be disclosed to an external service.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.