Call Academic Search Agent

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only academic research skill that uses search/scraping tools and creates wiki report files as part of its stated workflow.

Install only if you want an agent that performs academic-style searches, scrapes selected URLs, and saves a research log plus final report as wiki documents. Review important citations yourself, and avoid entering confidential or unpublished research topics if sending queries to external search tools or persisting logs would be a problem.

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 (2)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The skill metadata and overview are so generic that they do not meaningfully constrain when the skill should be invoked or what boundaries it should respect. In an agentic system, vague scope increases the chance of inappropriate invocation for unrelated tasks, which can trigger unnecessary tool use, external searches, file creation, and report generation on user input that was not intended for this workflow.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The instructions mandate creating and repeatedly appending to wiki documents throughout the workflow, then submitting those file paths, without requiring any user-visible notice or confirmation before writing persistent artifacts. That creates a clear risk of silent data persistence, accidental retention of sensitive user input or scraped content, and unexpected side effects from simply invoking the skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal