ClawHub

Marketing Psychology

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only marketing advice skill with no code or install hooks, though it may use a local product-marketing context file if present.

Before installing, review any .agents/product-marketing-context.md or .claude/product-marketing-context.md file because the skill may use that information in marketing recommendations. Also consider narrowing usage if you do not want persuasion-oriented guidance triggered by broad psychology terms.

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 activation description is unusually broad, with many generic trigger phrases such as 'psychology,' 'persuasion,' 'decision-making,' and 'social proof' that can match routine marketing conversations far outside a narrow intended use. Over-broad routing can cause this skill to activate unnecessarily and inject persuasion-oriented guidance into contexts where it was not requested, increasing the chance of inappropriate or manipulative recommendations.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The eval explicitly rewards activation on a vague request ('what psychological principles should I use...'), reinforcing a broad trigger surface for the skill. In an agent router, this can cause the skill to activate for loosely related prompts and override more appropriate skills, leading to misrouting and potentially unsafe or manipulative advice being applied outside the intended marketing context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal