ClawHub
Back to skill

Security audit

tophantppt

Security checks for vulnerabilities and agentic risk

Overview

This skill creates image-based PowerPoint decks using fixed GitHub background images, with a minor reliability/privacy caveat around repeated remote image fetching.

Installers should expect this skill to contact GitHub for background reference images and to send slide prompts/content to an image-generation workflow when used. In privacy-sensitive or offline environments, use caution because the artifact does not define retry limits or an offline fallback beyond a default remote image.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill mandates fetching remote reference images from external URLs and retrying until successful, yet it provides no user warning about network access, external resource dependency, or possible exposure of request metadata. In privacy-sensitive environments, repeated outbound requests may leak usage patterns, trigger unbounded retries, or violate network restrictions and user expectations.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill mandates fetching remote reference images from external URLs and retrying until successful, yet it provides no user warning about network access, external resource dependency, or possible exposure of request metadata. In privacy-sensitive environments, repeated outbound requests may leak usage patterns, trigger unbounded retries, or violate network restrictions and user expectations.

Static analysis

No suspicious patterns detected.