ClawHub
Back to skill

Security audit

AI-CMO Social Media Promoter

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI-CMO integration that sends a product URL or name to an external API to find social promotion opportunities, with privacy and public-posting risks users should manage.

Before installing, treat any submitted product name or URL as shared with AI-CMO's external service. Do not submit confidential, internal, or pre-launch information unless that sharing is approved, and review all generated comments yourself before posting publicly or using a brand 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states that analysis happens server-side, but it does not clearly warn users that the product URL or name they provide will be transmitted to a third-party service for processing. This can lead to unintended disclosure of confidential product plans, internal URLs, or sensitive business context, especially when users assume the skill operates locally or only within the agent environment.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

The skill sends user-supplied product identifiers and an API key to an external service over the network, which is a genuine external transmission path. In this skill's context, that behavior is expected, but it still carries security and privacy risk because submitted inputs may contain sensitive business information and the API key grants access to a third-party account.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Note: Analysis takes 2–4 minutes (scraping 6 platforms + AI scoring). Set your HTTP client timeout to at least 300 seconds.

typescript
const resp = await fetch("https://www.aicmo.site/api/v1/open/analyze", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This documentation extends beyond analysis and copy generation into concrete operational guidance for posting and engaging on third-party social platforms. That makes the skill more likely to facilitate coordinated promotional behavior, including account actions that may violate platform rules or be used for spammy/manual astroturfing workflows.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advises users on how to read posts, review comments, compose replies, and proceed through multiple engagements, but it does not warn that replies are public, can affect account reputation, and may expose user or brand information. In this context, the omission increases the chance of unsafe or non-compliant posting behavior because users are encouraged to act operationally without prominent safety caveats.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The sample request hard-codes language: "en", which nudges implementations toward a fixed language setting. Since the document also includes Chinese content and does not explain that users may choose their preferred language, this can conflict with language/locale choice expectations.

Content

No source excerpt is available for this finding.