ClawHub
Back to skill

Security audit

Mailchimp

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Mailchimp connector skill that discloses account access and state-changing actions, with confirmation rules for writes and deletion.

Install only if you intend to let the agent access your connected Mailchimp account through OOMOL. Treat read actions as potentially exposing subscriber or audience data, and require the agent to show the exact payload and target before any update, archive, tag change, upsert, or permanent deletion.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
78% confidence
Finding
The instruction to use this skill for "ANY Mailchimp request" is overly broad and can cause the agent to invoke a capability-bearing integration in situations where the user intent is vague, informational, or does not require account access. In context, this skill includes write and destructive actions, so over-triggering increases the chance of unnecessary account access or accidental state-changing operations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.