ClawHub
Back to skill

Security audit

Ad Copy Generator

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only ad copy helper with no executable code, credentials, persistence, or automatic account actions, but users should be careful with compliance-sensitive ad claims and the off-platform Pro upsell.

Install only if you want a simple prompt helper for drafting ads. Review any health, weight-loss, supplement, finance, or similar ad copy for truthfulness, evidence, and platform policy compliance before use. Treat the Telegram Pro package and its advertised Python scripts as separate, unreviewed material.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Low
Confidence
87% confidence
Finding
The skill explicitly encourages generation of ad copy for regulated or sensitive domains such as weight loss coaching and fitness supplements, but provides no guardrails around substantiation, compliance, or platform advertising policies. This can enable deceptive, non-compliant, or harmful claims that expose users to policy violations, consumer harm, and legal risk, especially because the examples include outcome-focused language commonly scrutinized by ad platforms and regulators.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.