pdf-image-extractor
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward local PDF image extractor that writes extracted or resized images to a configured output folder.
Install dependencies in a virtual environment, edit the hard-coded input and output folders before running, and test on non-sensitive PDFs first. Only use it on private documents if you are comfortable with their embedded images being written to the output directory.
SkillSpector
By NVIDIA
Vulnerability Patterns
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
66/66 vendors flagged this skill as clean.