ClawHub

Philosophy Dialogue Publish

Security checks across malware telemetry and agentic risk

Overview

This is a text-only philosophy persona-routing skill with broad triggers but no executable code, hidden data access, persistence, or credential handling.

Install only if you want the assistant to switch into philosopher or thinker-style viewpoints during relevant conversations. Be aware that its broad trigger phrases may activate when you discuss perspectives casually, and some referenced 243-person library content is not included in this submitted artifact.

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
90% confidence
Finding
The manifest description says that inputting any person's name can activate a corresponding perspective, which creates an overly broad activation surface and raises the risk of accidental invocation during normal conversation. In an agent environment, broad matching can cause the skill to trigger outside user intent, leading to confusing behavior, unwanted persona shifts, or unreviewed downstream skill loading.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrase '多视角讨论' is generic everyday language and is likely to collide with ordinary user requests that are not intended to invoke this specific skill. This increases the chance of unintended activation and can override more appropriate handling, especially in systems that rely on lightweight trigger matching.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal