ClawHub
Back to skill

Security audit

influencer-marketing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple influencer-marketing guidance document with no executable code, persistence, credential use, or hidden behavior.

Before installing, be aware that the skill may read local project-context files if present and may guide influencer discovery using external platforms or searches. This is consistent with its marketing purpose; review project-context files first if they contain sensitive business information.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says to use the skill when the user wants to 'plan, implement, or optimize influencer marketing strategy,' which is a broad natural-language condition without clear boundaries or exclusion cases. Although some specific keywords are listed, the open-ended intent phrasing could overlap with many general marketing requests and cause unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.