ClawHub
Back to skill

Security audit

Network Pharmacology

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its stated research-reporting purpose, but its generated HTML report has an unsafe rendering pattern that could execute crafted input data in a browser.

Review before installing. Use it only for projects where SciMiner calls and possible input uploads are acceptable, keep SCIMINER_API_KEY out of project files, and open generated HTML reports only from trusted input data or after the renderer is patched to avoid innerHTML for table-derived metrics.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding
This is a mismatch because the declared purpose describes a broad network-pharmacology analysis skill with evidence gathering, biological inference, and multiple analytic capabilities, while the provided code is narrowly a report-rendering utility. It does not access SciMiner, query external resources, perform pharmacology analysis, assess ADMET/off-targets, run docking, or build hypotheses from raw evidence. The only overlap is interactive network visualization and report generation, which is just one small part of the declared functionality.

Static analysis

No suspicious patterns detected.