Social Listening Report

Security checks across malware telemetry and agentic risk

Overview

This is a report-template skill for social listening and brand analytics, with no code execution, credential access, or hidden data movement found.

This is reasonable to install as a social listening report aid. Before using it with real exports or screenshots, remove unnecessary customer data, private identifiers, credentials, and confidential business details. Be aware it may activate for some broad marketing or analytics requests because its trigger text is wider than strictly necessary.

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
95% confidence
Finding
The activation text includes broad phrases like "monthly report," "trends analysis," and especially "any task involving structured interpretation of social or digital data," which overlap with many ordinary analytics or reporting requests outside this skill's intended scope. The file does not provide exclusion conditions or negative examples to clarify when the skill should not trigger.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal