ClawHub

Influence Principle Selector

Security checks across malware telemetry and agentic risk

Overview

This is a text-only persuasion analysis skill with disclosed ethical checks and no code, hidden data access, persistence, or account-changing behavior.

Install only if you want an advisory tool for ethical persuasion audits and strategy selection. Review outputs manually, use only real testimonials, credentials, limits, and claims, and do not use it to deceive, coerce, or target vulnerable people.

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
91% confidence
Finding
The skill description is written broadly enough to activate on many generic requests about persuasion, marketing, negotiation, or conversion improvement, which can cause over-invocation outside a tightly scoped context. In an agent environment, this increases the chance the skill is selected for sensitive influence or manipulation-related tasks without sufficient boundary checks, leading to unsafe guidance or policy bypass through misrouting.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The discovery triggers are framed as very general user intents such as making content more persuasive, understanding negotiation influence, or diagnosing conversion issues, without strong exclusion boundaries. Because the skill explicitly supports persuasion strategy selection and sequencing, broad routing can expose it to misuse in manipulative contexts and cause the agent to provide influence optimization advice where stricter safeguards should apply.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal