ClawHub
Back to skill

Security audit

Mixpanel

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for Mixpanel access, but its first-time setup includes unpinned remote shell installers that should be reviewed before use.

Review the oo CLI installer before running it, or prefer a package-manager or verified installer path if available. Install this only if you are comfortable granting the connector access to Mixpanel analytics data, including raw events and profile information, through your OOMOL-connected account.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs execution of a remote installation script via curl ... | bash, which is a classic high-risk pattern because it grants immediate code execution to whatever the remote server returns at that moment. In a skill context, this is more dangerous because the content may be followed automatically or semi-automatically during failure handling, turning an authentication/setup issue into arbitrary code execution on the host.

Content

Scanner excerpt · SKILL.md (reported line 67)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger language is overly broad, directing the agent to use this skill for effectively any Mixpanel-related task. That increases the chance the skill is invoked in situations where direct reasoning, narrower tooling, or stricter approval boundaries would be more appropriate, expanding the blast radius of any unsafe behavior in the skill.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Line L40 describes export_events as exporting raw Mixpanel events for a date range, which semantically indicates data retrieval rather than modifying Mixpanel state. This conflicts with the later safety guidance that [write] actions change Mixpanel state, creating intent confusion for users and agents deciding whether confirmation is needed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.