Report Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a local report generator for structured data files, with no evidence of hidden data access, network exfiltration, credential use, or persistence beyond generated report files.

Install this if you want a local Python helper for report generation. Run it from a project folder you trust, provide only the data files you intend to analyze, choose output paths deliberately, and install its Python dependencies from trusted package sources.

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
82% confidence
Finding
The skill uses very broad invocation language such as dashboards, KPI reports, executive briefs, and analytical reports, which can cause the agent to route many generic analytics requests into this skill. Overbroad matching increases the attack surface because the skill may be selected in situations it was not designed or permissioned to handle, potentially exposing user data to unnecessary file processing or misleading outputs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal