biostartechnologylinkedin

Security checks across malware telemetry and agentic risk

Overview

This is a LinkedIn post-writing helper made of markdown instructions only, with no code execution, credential access, account control, or persistence.

Safe to install for LinkedIn drafting. Review generated posts before publishing, verify any business metrics or claims, and confirm the package identity if the metadata mismatch matters to you.

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: 90% confidence
Finding: The skill description is broad enough to match a wide range of ordinary writing requests, which can cause the agent to invoke this skill in situations where it was not specifically intended. Over-broad routing increases the attack surface because a prompt-injection-prone or overly assertive skill may be selected more often than necessary, and here the scope includes many generic content-creation tasks across "any professional niche."

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal