ClawHub
Back to skill

Security audit

Kakiyo Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a legitimate Kakiyo integration, but it gives an agent broad authority to change outreach campaigns, clients, webhooks, and workspaces without clear confirmation safeguards.

Install only if you trust Kakiyo with your LinkedIn outreach and account data. Before letting an agent use it, require confirmation for create, update, delete, invite, webhook, batch prospect, and campaign or agent pause/resume actions, and verify workspace IDs, campaign IDs, recipients, and webhook URLs before execution.

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
  • 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 (3)

External Transmission

Medium
Category
Data Exfiltration
Content
**Once user provides their API key, run:**
```bash
mcporter config add kakiyo https://api.kakiyo.com/mcp \
  --header "Authorization:Bearer USER_API_KEY"
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
**Once user provides their API key, run:**
```bash
mcporter config add kakiyo https://api.kakiyo.com/mcp \
  --header "Authorization:Bearer USER_API_KEY"
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill exposes numerous state-changing and externally impactful actions such as creating campaigns, inviting clients, assigning agents, deleting workspaces, and configuring webhooks, but it provides no explicit guidance to require user confirmation before performing destructive or organization-wide operations. In an agent-executed context, this increases the chance of unintended outreach, deletions, or account changes caused by ambiguous prompts or over-automation.

Static analysis

No suspicious patterns detected.