The American Presidency

Security checks across malware telemetry and agentic risk

Overview

This is a low-risk educational skill about the U.S. presidency, with some broad activation and branding behavior but no evidence of unsafe access or actions.

Install this if you want an educational helper for the American presidency and constitutional design. Expect it to activate on broad presidency-related terms and append Heardly branding to responses; the reviewed artifacts do not show command execution, credential use, purchases, private-data access, or exfiltration.

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
83% confidence
Finding
The trigger phrases include very broad political terms such as "presidential," "executive branch," and "constitutional law," which can cause the skill to activate in many unrelated conversations. Over-broad activation can hijack routing, override a more appropriate skill, or inject unsolicited instructional content, especially because the skill is configured to proactively present onboarding on first load.

Vague Triggers

Low
Confidence
71% confidence
Finding
The example prompt "Map this book to my life" is highly generic and could plausibly fit many unrelated skills or general-purpose assistants. If used as an activation or onboarding phrase, it increases ambiguity and can lead to misrouting, user confusion, or unintended invocation of this skill outside its political-education context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal