Content Repurposer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only writing helper for turning long-form content into social posts, with no code execution, account access, or publishing authority.

Use this as a drafting aid and review outputs before posting, especially claims, hashtags, tone, and platform fit. Do not treat the embedded approval/signature text as independently verified provenance.

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 (2)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests like 'create social posts' or 'adapt for social,' which can cause unintended activation of this skill in contexts where the user did not explicitly request this specific workflow. In an agent system with multiple skills, ambiguous activation can route sensitive or unrelated content into a transformation pipeline, causing incorrect behavior, privacy exposure, or bypass of more appropriate safeguards.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The activation logic is underspecified and only describes when the skill should activate, not when it must refuse activation. That ambiguity increases the chance of over-triggering on general requests involving long text, social media, or threading, which can make the agent choose this skill unexpectedly and mishandle user intent or data.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal