ClawHub
Back to skill

Security audit

Autoplot Skill自动数据可视化

Security checks across malware telemetry and agentic risk

Overview

This is a local chart-generation skill that reads user-selected data files and writes visualization files, with no evidence of hidden network access or credential use.

Install this if you want a local helper for turning data files into charts. Use explicit input and output paths, and be careful with sensitive datasets because generated HTML or image files may preserve or reveal parts of the underlying data.

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
90% confidence
Finding
The trigger phrases are broad enough to match ordinary requests like 'analyze and visualize this data' or 'show me trends,' which can cause the skill to run when the user may have intended a safer, more general analysis flow. Because this skill reads user-supplied files and writes outputs to disk, unintended invocation increases the chance of unnecessary file access and artifact creation.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The description advertises generated PNG, SVG, HTML, and PDF outputs but does not clearly warn that these artifacts are written to disk. Users may unknowingly cause local file creation, leading to privacy, workspace clutter, or persistence issues, especially for HTML outputs that may embed sensitive data.

VirusTotal

No VirusTotal findings

View on VirusTotal

Static analysis

No suspicious patterns detected.