ClawHub
Back to skill

Security audit

Content Calendar Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple social content calendar prompt with no code execution, credential access, persistence, or hidden data handling.

This appears safe to install for drafting social media calendars. Review generated posts before publishing, especially because the skill can draft public-facing content and its posting-time and reach suggestions are heuristic rather than verified account-specific analytics.

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
Confidence
83% confidence
Finding
The notes specify platform-specific output constraints but only describe English-language style assumptions and formatting conventions, with no indication that users can choose another language or locale. This can be read as forcing a default language/locale behavior without explicit opt-in, which falls under the language/locale policy category.

Static analysis

No suspicious patterns detected.