ClawHub
Back to skill

Security audit

bd1

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent brand-analysis skill whose main side effect is a disclosed PowerPoint file saved to a hardcoded desktop path.

Before using it, confirm where PPT files should be saved and avoid the hardcoded Lenovo desktop path if it does not match your machine. Only provide confidential brand or business material if you are comfortable with it being included in a generated local presentation, and install pptxgenjs only from a trusted npm source if needed.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill mandates generating a .pptx file and writing it to a fixed desktop path, which expands a text-analysis skill into performing local file-system actions. Even if the content is benign, forced file creation without explicit per-run consent can cause unintended writes, overwrite collisions, privacy issues, or abuse when the analyzed content is sensitive.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs saving results to the user's desktop without any user notification or confirmation, creating an unconsented local side effect. In context, this is more dangerous because the trigger conditions are broad, so a user asking for ordinary brand analysis could unknowingly cause local file creation and possible exposure of sensitive business content in a visible location.

Static analysis

No suspicious patterns detected.