ClawHub
Back to skill

Security audit

Coloring page

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple image-to-coloring-page wrapper with disclosed use of a Gemini image model and no artifact-backed persistence or hidden behavior.

Install only if you are comfortable providing a Gemini API key and having uploaded photos processed by the Gemini image model. The reviewed artifact does not show hidden persistence or destructive behavior, but it references an external CLI/underlying skill that should also be present and trusted for the skill to work.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
# coloring-page

Create a printable black-and-white outline coloring page from a photo.

This skill is designed to be used conversationally:
- You upload an image

Static analysis

No suspicious patterns detected.