ClawHub
Back to skill

Security audit

Google Scholar Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward academic-paper search helper that sends user searches to Semantic Scholar, with minor naming and privacy-disclosure issues but no evidence of hidden or destructive behavior.

Install only if you are comfortable sending academic search terms and paper IDs to Semantic Scholar. Do not use confidential project names, sensitive research topics, or private identifiers as queries unless third-party API sharing is acceptable in your environment.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill metadata and documentation do not cleanly match the described behavior, including naming it 'google-scholar-search' while claiming Semantic Scholar usage and advertising capabilities not evidenced in the provided content. Description-behavior mismatches are dangerous because they mislead reviewers and users about what external service is contacted and what data flows or actions occur, which can hide unauthorized network behavior or unreviewed functionality.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises and demonstrates network-capable behavior but does not declare any explicit tool scope or permissions boundary. In an agent environment, this can lead to overbroad or implicit network access, making it harder to review, sandbox, and constrain outbound requests to only the intended academic API.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/API.md (reported line 6)May include surrounding context.

Base URL

text
https://api.semanticscholar.org/graph/v1

Rate Limits

External Transmission

Medium
Category
Data Exfiltration
Confidence
86% confidence
Finding

The script transmits user-supplied search terms and paper identifiers to an external API over the network. While this is expected for a search skill, it is still a real data egress point that can expose sensitive research topics, internal project names, or other confidential inputs if users assume searches remain local or are sent to a different provider.

Content

Scanner excerpt · scripts/search_papers.py (reported line 14)May include surrounding context.

python
import time
from typing import List, Dict, Optional

BASE_URL = "https://api.semanticscholar.org/graph/v1"
HEADERS = {
    'User-Agent': 'OpenClaw-GoogleScholarSearch/1.0'
}

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata advertises Google Scholar search, but the implementation sends queries to the Semantic Scholar API instead. This mismatch is a security-relevant integrity and transparency issue because user queries and research interests are transmitted to a different third party than the user or operator may expect, undermining informed consent and trust boundaries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README instructs users to search academic papers via the Semantic Scholar API but does not disclose that user-entered search terms will be sent to a third-party service. While this is not code execution or credential theft, it is a real privacy/transparency issue because users may submit sensitive research topics, internal project names, or other confidential queries without realizing they leave the local environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.