Content Repurposer

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward content-repurposing skill that fetches user-supplied URLs or reads chosen text files to generate social-media outputs.

Install this if you want a local tool that can fetch article URLs, read selected text or markdown files, and optionally write generated posts to an output folder. Use trusted URLs, do not point it at secrets or private files unless you intend that content to be transformed, and choose output folders where overwriting twitter.txt, linkedin.txt, and similar files is acceptable.

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: 80% confidence
Finding: The description and usage text are broad enough that the skill may be invoked for generic writing or content-generation requests, not just repurposing user-provided articles. Over-broad triggering can expose file/network functionality in contexts where the user did not intend to fetch URLs or process local content, leading to unnecessary data exposure or surprising actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal