ClawHub
Back to skill

Security audit

Dataify Task Result

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrow Dataify helper that downloads one completed task result using a disclosed API token and fixed endpoint.

Install only if you intend this agent to use your DATAIFY_API_TOKEN to fetch Dataify task results. The returned JSON may contain scraped data, so review what task ID you provide and where the agent will display or store the response.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to read an environment variable and make a network request, but it declares no permissions or trust boundaries for those capabilities. That mismatch can cause the agent to access secrets and external services without clear user visibility or policy enforcement, increasing the risk of unintended data exposure or unauthorized outbound requests.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.