ClawHub
Back to skill

Security audit

Pdf Figure Extractor

Security checks across malware telemetry and agentic risk

Overview

This skill is a narrow local workflow for extracting clean figures from academic PDFs, with no evidence of hidden access, networking, persistence, or destructive behavior.

Install only if you want an agent to process local academic PDFs and save cropped figure images. Use it on PDFs you intend to analyze, specify a safe output location, and review the generated images for accidental inclusion of captions, text, or sensitive content.

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

Medium
Confidence
90% confidence
Finding
The trigger keywords are generic and lack clear scoping, so the skill may activate on broad PDF/image-extraction requests outside the intended academic-paper workflow. That can cause the agent to invoke this skill in the wrong context, leading to incorrect file handling, unintended processing of arbitrary PDFs, or interference with safer or more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal