ClawHub
Back to skill

Security audit

Ai Company Cmo 3.0.0

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed marketing-governance skill with broad permissions, but the inspected artifact is markdown-only and shows no hidden execution, persistence, credential use, exfiltration, or destructive behavior.

Install this only if you want a broad CMO-style marketing strategy skill that may activate on common marketing terms. Review the requested file read/write, network API, session messaging, and subagent permissions in your environment, and prefer explicit invocation when working near sensitive business, customer, or campaign data.

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
  • 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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list contains broad generic terms such as "CMO", "营销", "品牌", and "增长" that are likely to appear in many unrelated conversations. This can cause accidental invocation of a high-permission skill that has file read/write, network API, and subagent/session capabilities, expanding attack surface and enabling unintended actions in contexts where the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.