Sentiment Monitor

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  0.4.0

Overview

This skill is an instruction-only public sentiment reporting workflow that uses public web research and saves a local HTML report.

Install only if you are comfortable with the agent searching public web sources about a person, show, brand, or product and saving a local HTML report. Treat exact social metrics cautiously: the skill tells the agent to use only numbers visibly available from public sources and mark missing data as unavailable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger conditions are very broad and include generic terms like public opinion, sentiment, and reputation, which can cause this skill to activate for requests outside its intended scope. Over-broad activation can route unrelated user tasks into web collection and report generation flows, increasing the chance of inappropriate data gathering, misleading outputs, or unsafe task capture by the wrong skill.

VirusTotal

65/65 vendors flagged this skill as clean.