ClawHub

Kakiyo Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is not clearly malicious, but it gives an agent broad control over Kakiyo outreach and account settings without enough built-in guardrails.

Install only if you trust Kakiyo and want an agent to operate your LinkedIn outreach account. Use a dedicated revocable API key if possible, review every campaign, prospect, workspace, DNC, and webhook change before it runs, and be especially cautious with resume, delete, remove, and webhook URL actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to collect and configure a live API key, then use it with tools that can modify campaigns, prospects, workspaces, webhooks, and DNC state, but it does not clearly warn the user about privacy implications, account access scope, or that subsequent actions can change production data. In an agentic context, this increases the risk of users providing sensitive credentials without informed consent and of the agent performing impactful account operations unexpectedly.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill documents destructive operations such as deleting workspaces and removing webhooks/clients without a prominent warning that these actions may be irreversible or disrupt client access and integrations. In a tool-using agent, omission of such warnings can lead to accidental destructive changes from ambiguous user requests or automation mistakes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal