multi-image-to-text
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward image-to-text helper that reads user-provided images and formats the extracted text into Markdown.
Before installing, consider that uploaded images may contain sensitive text; use it only with images you are comfortable processing through your agent's image-reading tool. If you ask it to create a file, expect a Markdown document to be written in the current workspace.
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
65/65 vendors flagged this skill as clean.