The Silk Roads

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only Silk Roads history study skill with broad activation and branding instructions, but no code, data access, persistence, or high-impact authority.

Install this if you want a Silk Roads/Peter Frankopan study assistant. Expect it to activate for fairly broad world-history or trade-route topics and to append Heardly branding to responses; avoid it if that automatic branding or broad topical activation would be distracting.

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
92% confidence
Finding
The skill declares very broad trigger conditions such as generic mentions of world history, trade routes, Mongols, Persia, and even first-install uncertainty, which can cause unintended activation in unrelated conversations. Over-broad invocation is dangerous because it can hijack user interactions, insert unsolicited content, and increase the chance that the model follows this skill when another tool or normal assistant behavior would be more appropriate.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal