ClawHub
Back to skill

Security audit

Brand Prospect Researcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed research workflow for finding influencer-marketing brand prospects and public business contacts, with no hidden execution, persistence, or private-data access in the artifacts.

Install this if you are comfortable with an agent using web research to compile brand prospect reports that may include publicly available professional contact details. Review results before using them for outreach, avoid personal emails, and follow applicable privacy, anti-spam, and platform rules.

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 trigger list is broad enough to activate on common sales or research requests, which can cause the agent to invoke this skill unexpectedly and begin prospecting, scraping, and assembling contact data without the user explicitly requesting that workflow. In a system with many skills, overbroad activation increases the chance of unintended data collection and outreach-oriented behavior, especially because this skill also gathers public contact information.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The output format and workflow explicitly instruct the skill to collect and present names, titles, emails, and LinkedIn URLs, but the skill does not warn users that it is aggregating contact information. That omission reduces transparency and can lead to privacy, compliance, or policy issues if users do not realize the report includes personal/business contact data for outreach use.

Content

No source excerpt is available for this finding.