ClawHub
Back to skill

Security audit

Marketing Genius

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple marketing-copy helper that discloses sending product and audience details to an external API and does not include executable code or persistence.

Install only if you are comfortable sending the product description or URL and target audience to the disclosed third-party API. Do not use it with confidential launch plans, sensitive customer data, or proprietary strategy unless that external service is approved for such data.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is broad enough to trigger on a wide range of user requests involving 'marketing insights, ad copy, or value propositions,' which can cause unintended activation outside a narrowly defined use case. Over-broad routing increases the chance that unrelated or sensitive prompts are sent to this skill and then forwarded to the external API, creating data-handling and prompt-routing risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The usage instructions prescribe a Chinese invocation format without explaining language selection or offering a neutral alternative, which can bias activation behavior and reduce user awareness of how the skill is being invoked. In multi-skill systems, rigid language-specific invocation can cause accidental triggering, confusion, or bypass of normal user-choice and review patterns, though the security impact here is limited.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.