ClawHub
Back to skill

Security audit

marketing-psychology

Security checks for vulnerabilities and agentic risk

Overview

This is a content-only marketing psychology skill with disclosed, purpose-aligned guidance and no executable code, persistence, or hidden data movement.

Install only if you want an agent to apply behavioral science to marketing work. Review outputs for ethical use: avoid fake scarcity, misleading social proof, coercive defaults, and manipulative pricing or subscription patterns.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The manifest description is extremely broad and includes many common marketing and psychology terms, increasing the chance this skill is invoked in loosely related contexts. Over-broad activation can route users into persuasion-oriented guidance unexpectedly, which raises the risk of manipulative recommendations being applied where a narrower or more appropriate skill should have been used.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This section operationalizes persuasion techniques such as scarcity, defaults, anchoring, loss aversion, decoys, and other behavior-shaping patterns without meaningful guardrails or an upfront warning about manipulation, dark patterns, or user harm. In context, the skill explicitly teaches how to influence decisions, so the absence of strong ethical constraints makes misuse for deceptive or coercive marketing materially easier.

Vague Triggers

Medium
Confidence
94% confidence
Finding
This JSON manifest-like file includes an expected behavior that the skill 'Should trigger on casual phrasing' and asserts 'Triggers on casual phrasing.' That activation guidance is overly broad and overlaps with everyday speech, without any limiting context or negative examples to clarify when the skill should or should not activate.

Static analysis

No suspicious patterns detected.