Back to skill

Security audit

Excalidraw Handdraw

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a local Excalidraw diagram generator with expected Docker and file-writing behavior, but users should confirm output paths before use.

Install only if you are comfortable with a skill that can start a local Docker-based canvas service and save or insert generated diagrams into workspace files. Confirm destination paths, avoid overwriting existing files unintentionally, and stop the local container when finished if you do not need it running.

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
92% confidence
Finding
The skill advertises very broad trigger phrases such as '画图' and '创建图表', which can match ordinary user requests and cause the skill to activate in contexts the user did not explicitly intend. Because this skill can start Docker, write files, move outputs, and modify Markdown content, accidental invocation expands the chance of unintended side effects beyond simple read-only behavior.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to move generated files into user-specified locations and insert image links into Markdown without requiring confirmation about overwriting existing files or modifying documents. In practice, this can lead to unintended file replacement or silent content changes, especially when combined with broad triggering and user-provided paths.

VirusTotal

56/56 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.