ClawHub
Back to skill

Security audit

dataify-google-scholar

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Google Scholar-to-Dataify API helper with user confirmation before calls and no hidden persistence or unrelated data access found.

Install this if you want an agent to submit confirmed Google Scholar searches to Dataify. Review the confirmation table before approving a call, and only provide a Dataify token you are comfortable using for these requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs the agent to read environment variables, invoke local Python scripts, read reference files, and make external network requests, yet no declared permissions are present. This creates a capability/permission mismatch that can lead to over-privileged execution, unclear trust boundaries, and accidental access to secrets such as DATAIFY_API_TOKEN without explicit governance.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger condition is broad enough to activate on generic phrases like 'paper search' or mentions of the academic search field, which can cause the skill to run in contexts the user did not clearly intend. In a skill that can read tokens and initiate networked API calls, ambiguous activation increases the chance of unintended data disclosure or third-party requests.

Natural-Language Policy Violations

Medium
Confidence
79% confidence
Finding
The skill requires a Markdown table with fixed Chinese column headers for user-facing confirmation without checking the user's language preference. This is primarily a UX and consent clarity issue: users may misunderstand parameters they are being asked to confirm, which is more concerning here because the confirmation gate precedes a real external API call.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.secret_argv_exposure

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.md:60

Instructions pass high-value credentials through process argv.

Critical
Code
suspicious.secret_argv_exposure
Location
SKILL.zh-CN.md:62