ClawHub
Back to skill

Security audit

Framing Effect

Security checks across malware telemetry and agentic risk

Overview

This is a text-only educational skill about recognizing and auditing framing effects, with some persuasion-related guidance but no hidden code, data access, or persistence.

Install this as an educational decision-audit skill, not as a license to manipulate people. When using it to write persuasive messages, present materially equivalent frames, avoid omitting facts, and use it to make tradeoffs clearer rather than to exploit a reader's bias.

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

Medium
Confidence
91% confidence
Finding
This example goes beyond neutral explanation and explicitly teaches how framing can be used to steer conclusions in political, commercial, legal, and negotiation contexts, including claims like 'People who can choose the frame can usually choose the conclusion.' In a skill intended to help write persuasive messages, presenting these tactics without clear warnings, counterbalances, or ethical constraints can facilitate manipulative influence over user decisions rather than informed analysis.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.