ClawHub
Back to skill

Security audit

product-hunt-playbook

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Product Hunt launch advice skill with some promotional links, but no hidden execution, credential access, persistence, or destructive behavior.

Review the skill as a marketing playbook, not a self-contained guaranteed launch system. Expect some links to paid resources and coaching, and be careful to keep any Product Hunt outreach authentic and compliant with platform rules.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The manifest describes this skill as containing a Product Hunt ranking deep-dive, launch checklist, voter mobilization guidance, asset templates, and a 72-hour momentum plan. In this file, most of the substantive content instead advertises external GitHub, Gumroad, and paid coaching resources, so the documented behavior/content does not match the claimed self-contained playbook scope.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest describes a substantive playbook covering ranking mechanics, launch-day checklists, mobilization strategies, templates, and post-launch operations. In this file, most of the content instead advertises external free/premium resources and paid coaching services, with little actual operational guidance present.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list includes "launch day," which is a common phrase used in many contexts beyond Product Hunt. Because the file does not provide exclusion conditions or narrow the trigger to Product Hunt-specific contexts, this could cause unintended activation.

Natural-Language Policy Violations

Low
Confidence
86% confidence
Finding
The entire skill description is presented only in Korean, with no indication that users can choose another language or that the locale restriction is intentional and justified. This can violate a language/locale policy when skills are expected to avoid forcing a specific language without user opt-in.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.