ClawHub

特朗普.skill - 谈判与权力思维操作系统

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only Trump perspective analysis and roleplay skill with no executable behavior, though its broad triggers may activate political framing more often than users expect.

Install this only if you want Trump-style political analysis or roleplay. Treat outputs as simulation and commentary, verify factual or predictive claims independently, and be aware that broad Trump-related prompts may activate the skill's framing.

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
89% confidence
Finding
The trigger phrases are broad and overlap with ordinary discussion about Trump, so the skill may activate when the user did not intend to invoke a specialized persona or analysis mode. That creates control-boundary problems: the assistant can be steered into roleplay or opinionated framing unexpectedly, which is especially risky for a politically charged persona with strong rhetorical instructions.

Vague Triggers

Medium
Confidence
94% confidence
Finding
Routing all ambiguous input into analyst mode removes a clear consent boundary and effectively broadens activation to uncertain contexts. This can cause unintended skill execution, biased framing, or persona leakage into normal conversations, increasing the chance of unsafe or misleading outputs without explicit user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal