ClawHub
Back to skill

Security audit

Framing Effect

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable thinking skill about recognizing and testing framing effects, with persuasion-related content that is disclosed and aligned with its purpose.

Install this as a decision and communication aid, not as a license to manipulate. When using it for persuasion, present equivalent alternative frames, avoid misleading omissions, and be especially careful in medical, financial, legal, political, or high-stakes contexts.

SkillSpector

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
89% confidence
Finding
This markdown file explicitly advises that communicators can 'choose the conclusion' by choosing the frame and recommends selecting frames to produce desired behaviors. Because markdown files should warn about behaviors that could affect user autonomy or decision integrity, the absence of any caution about manipulative use is a missing user warning.

Static analysis

No suspicious patterns detected.