Deep Research

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed deep-research skill that uses a local Python ledger to track research work, with no evidence of hidden access, exfiltration, or unsafe automation.

Install only if you want a structured research workflow that may browse external sources and log research notes. Keep run directories in a workspace, avoid logging secrets or unnecessary personal data, and use the reset option only on directories intended for research artifacts.

SkillSpector

By NVIDIA

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 96% confidence
Finding: The skill instructs the agent to perform network research, read local files, and write run artifacts via a Python ledger script, but it declares no permissions. This creates a capability/permission mismatch that can bypass user expectations and platform policy enforcement, especially because the skill explicitly encourages broad retrieval from untrusted sources and local files.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal