ClawHub
Back to skill

Security audit

学术全能搜

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent academic literature search helper that uses disclosed external research APIs, with no hidden persistence or unrelated local access found.

Install only if you are comfortable sending search terms to the selected academic providers. Avoid sensitive internal project names or regulated research topics unless your organization permits those providers, and set Baidu or Semantic Scholar API keys only if you want those integrations enabled.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares only Read,Bash, but its documented behavior clearly relies on environment variables, network access to multiple third-party services, and likely file output paths such as BibTeX export or piped summaries. This mismatch weakens security review and user understanding because the real capability surface is broader than what the metadata suggests.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs users to configure a third-party API key and states that Baidu Scholar results may include AI-generated summaries, but it does not warn that queries and possibly retrieved content may be transmitted to external providers. This creates privacy and compliance risk, especially for sensitive research topics, internal project names, or regulated data.

Natural-Language Policy Violations

Medium
Confidence
85% confidence
Finding
The skill mandates automatic routing of Chinese queries to Baidu Scholar + CrossRef without user consent. Automatic provider selection can send user queries to external services based on language characteristics alone, which is risky when queries contain sensitive subjects or when users have jurisdictional, privacy, or provider-preference constraints.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/commands.md:47

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/routing-guide.md:39

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
scripts/baidu_scholar_api.py:10