Security audit
Security checks for vulnerabilities and agentic risk
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.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Once user provides their API key, run:
mcporter config add kakiyo https://api.kakiyo.com/mcp \
--header "Authorization:Bearer USER_API_KEY"
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
Once user provides their API key, run:
mcporter config add kakiyo https://api.kakiyo.com/mcp \
--header "Authorization:Bearer USER_API_KEY"
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.
No suspicious patterns detected.