marcus-linkedin-writer

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only LinkedIn writing helper with a broad activation description but no code, credentials, posting ability, or system access.

Install this if you want a Marcus Wang LinkedIn drafting persona. Invoke it explicitly for Marcus-related LinkedIn posts, and review generated drafts for factual accuracy, confidentiality, and brand fit before publishing.

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: 95% confidence
Finding: The manifest description contains broad trigger phrases such as 'write a post' and topic-based matches that could activate this skill for ordinary content requests beyond Marcus-specific LinkedIn drafting. Over-broad activation can cause unintended skill invocation, leading to prompt hijacking of unrelated workflows, misrouting of user requests, and unnecessary exposure of embedded persona/instruction content.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal