ClawHub
Back to skill

Security audit

visual-content

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill that gives visual content planning guidance and does not add execution, persistence, or credential access.

Before installing, expect this skill to activate for a wide range of visual-content planning requests and to consult local project visual identity context when available; no hidden execution or persistence was found.

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
Confidence
90% confidence
Finding
The description says to use the skill whenever the user wants to plan, create, or repurpose visual content across channels, and includes generic phrases like "visual content" and "image for social post." This trigger scope is broad and lacks exclusion conditions or negative examples, which could cause the skill to activate for many ordinary image-related requests that may belong to other, more specific skills.

Static analysis

No suspicious patterns detected.