Copywriting Pro

Security checks across malware telemetry and agentic risk

Overview

This is a transparent copywriting guide with no code or account access, but users should apply it ethically and verify claims before publishing.

Install only for marketing and sales copy work. Before using output publicly, verify every claim, statistic, deadline, scarcity statement, testimonial, guarantee, and health or financial implication. Avoid applying the agitation guidance to vulnerable audiences or sensitive topics, and do not paste confidential customer records into the skill or external readability tools without permission.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The file instructs writers to "rub the wound" and emphasize the full cost of inaction, which operationalizes emotional pressure as a persuasion tactic without any guardrails around vulnerable audiences, truthfulness, or proportionality. In a copywriting skill, this is more dangerous because it is presented as reusable best practice and can normalize coercive messaging in ads, emails, and sales content at scale.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The PAS section explicitly says to stay in the agitation step "longer than feels comfortable," which encourages intentionally heightening distress to drive action rather than informing the user. That crosses from normal marketing structure into coercive pressure, and in this skill context it is especially risky because it can be directly copied into persuasive content for sensitive products or vulnerable audiences.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal