ClawHub
Back to skill

Security audit

Dataify Indeed Companies Info

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Dataify integration for creating Indeed company-information collection tasks, with expected token and network use.

Install only if you intend to use Dataify for Indeed company-data collection. Treat the Dataify API token as a secret, confirm parameters before submission, and only agree to saving DATAIFY_API_TOKEN permanently if you are comfortable storing that credential in your environment or shell profile.

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
93% confidence
Finding
The skill instructs the agent to access environment variables and make outbound network requests, but no permissions are explicitly declared. That creates an authorization gap: a user invoking the skill may not realize it can read local secrets such as DATAIFY_API_TOKEN and transmit data to an external API endpoint. In this context, the behavior is central to the skill’s function, so it appears operational rather than malicious, but it still increases risk because secret access and exfiltration paths are not transparently constrained.

VirusTotal

63/63 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:58