SciProjDesigner

Security checks across malware telemetry and agentic risk

Overview

This is a research-advice skill for computational drug discovery, with broad activation wording but no evidence of hidden execution, credential access, persistence, or data theft.

Installers should expect this skill to activate broadly for drug-discovery, molecular-modeling, structural-biology, and related Python debugging requests. Treat its scientific recommendations as expert-style drafting or review support, not as validated research conclusions; independently verify methods, citations, and safety-critical scientific decisions.

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

High

Confidence: 92% confidence
Finding: The trigger criteria are extremely broad and include many common terms from computational biology, chemistry, and code review, which can cause this skill to activate outside its narrowly intended use. Over-broad invocation can route unrelated or lower-risk requests into a highly specialized instruction set, leading to inappropriate guidance, unexpected file loading, or policy/scope bypass through misclassification of user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal