ClawHub
Back to skill

Security audit

IceCube Content Factory

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only content-writing skill with no executable code or sensitive access; the locale-specific example is a minor disclosure note, not a security concern.

Install this if you want help drafting social media content. Review generated posts before publishing, especially platform-specific language, hashtags, claims, and engagement hooks, because the skill optimizes for attention and may need user judgment to avoid overstatement or unwanted localization.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The Xiaohongshu example presents Chinese title, hook, and hashtags as a built-in output mode, but the document does not state that language selection is user-chosen or optional. This can violate language/locale policy expectations because the skill appears to prescribe a specific locale-specific output style without explicit opt-in.

Content

No source excerpt is available for this finding.