Academic Writing

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only academic writing skill with no code execution, credentials, persistence, or hidden high-impact behavior.

This skill appears safe to install for academic writing help. Review the strict citation and formatting rules before use, and be aware that citation verification may require browsing academic sources. Treat the external setup link and optional manual GitHub clone as informational unless you independently trust and review that repository.

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: 87% confidence
Finding: The skill has broad, always-on behavioral instructions but does not define clear activation conditions, allowed task boundaries, or refusal criteria. In an agent environment, this ambiguity can cause the skill to be applied in unintended contexts, increasing the chance of overreach, policy conflicts, or misuse of academic-style authority for tasks outside its intended scope.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal