ClawHub
Back to skill

Security audit

Generating Publication Ready Figures In R

Security checks across malware telemetry and agentic risk

Overview

This skill is a focused R plotting guide for making ggplot2 figures publication-ready, with no evidence of hidden execution, credential access, persistence, or data exfiltration.

Safe to install as plotting guidance. Before running README commands that source R files or install packages, verify the referenced files and repository are the ones you intend to trust, since those helper R files are not included in this reviewed bundle.

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 (1)

Vague Triggers

Low
Confidence
91% confidence
Finding
The invocation examples are phrased broadly enough that the skill could trigger on generic requests like 'make this figure publication-ready' without clear boundaries about required context, inputs, or when not to activate. In an agent environment, over-broad activation can cause unintended tool use or the skill being selected for adjacent tasks it was not meant to handle, increasing the chance of incorrect modifications or unsafe delegation.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.