ClawHub
Back to skill

Security audit

Social Media Content Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple branded social-media image generator that reads local templates and writes PNG files, with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you want a local tool that generates branded social-media PNGs. Review the output path before running so files are written where you expect, and treat the broad trigger wording as documentation that should be clarified if used in automation.

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
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The listed triggers ('Scheduled content calendar', 'Manual CLI execution', 'API trigger') describe general invocation channels rather than specific activation conditions or scoped trigger phrases. The file does not explain when the skill should or should not run, nor does it provide constraints or exclusion conditions, which could lead to unintended invocation in broader automation contexts.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest description frames the skill as generating social media posts for two brands, which implies textual post content. The implementation primarily creates PNG graphics with PIL and writes them to disk, producing branded images/carousels rather than social media post copy.

Intent-Code Divergence

Low
Confidence
88% confidence
Finding
The top-level docstring says "Social Media Content Generator for OpenClaw," but the manifest and code are scoped to LevelUpLove and PayLessTax. This is an active documentation mismatch that misstates the skill's intended target brands.

Static analysis

No suspicious patterns detected.