Academic Writing

Security checks across malware telemetry and agentic risk

Overview

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

Install it if you want academic-writing responses with strict Markdown, citation, and <ama-doc> formatting. For real scholarly work, manually verify citations and source quality because the skill asks for verifiable references but cannot guarantee every generated citation is correct.

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: 89% confidence
Finding: The skill’s activation scope is extremely broad: it presents itself as a general academic writing expert without defining when it should or should not be invoked. In agent systems, overly broad skills can be selected in inappropriate contexts, causing instruction hijacking of normal task routing, excessive authority over unrelated prompts, or policy bypass through format and citation mandates that are always-on rather than context-bounded.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal