ClawHub
Back to skill

Security audit

Fizzy

Security checks across malware telemetry and agentic risk

Overview

This is a normal Fizzy project-management CLI skill, but it can change or delete workspace data if the agent is given write-capable credentials.

Install this only if you want an agent to manage your Fizzy workspace. Use the least-privilege token available, protect any config file that stores it, and confirm exact board/card/comment IDs before deletes, read-all actions, uploads, downloads, or other write operations.

SkillSpector

By NVIDIA
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 (2)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is overly broad: phrases like 'boards, cards, tasks, backlog or anything Fizzy' can cause the agent to invoke this skill for loosely related conversation, increasing the chance of unnecessary access to a write-capable external system. Because the skill exposes create, update, delete, assignment, comment, and notification actions, accidental triggering could lead to unintended data access or modification.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents destructive commands such as board/card/comment/step/reaction/column deletion and bulk state-changing actions without warning about irreversible effects or requiring confirmation. In an agent setting, this increases the risk that a natural-language request is translated directly into destructive CLI operations, causing data loss or unwanted workflow changes.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.