Content Repurpose

Security checks across malware telemetry and agentic risk

Overview

This is a drafting-only content repurposing skill with no executable code, account access, or automatic posting behavior.

Safe to install as a drafting aid. Review generated posts before publishing, especially target language, factual claims, audience fit, and any business, legal, or reputational wording.

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

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The skill explicitly defaults output language by platform ('for Chinese platforms, use simplified Chinese; for Twitter/X, default to English unless the audience is Chinese-speaking') without requiring user confirmation. This can cause unintended disclosure, mis-targeted publication, or user surprise in multilingual or regulated contexts, especially if the source content contains nuanced messaging that should not be auto-localized or language-switched.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal