ClawHub
Back to skill

Security audit

GTM Account Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward account-research prompt that uses web research to create sales briefs, with no code execution or persistence.

Install this if you want an agent to perform web-based account research for sales or ABM preparation. Be aware that broad meeting-preparation prompts may invoke it, so users should provide a clear company name and review sourced outputs before relying on them, especially for people and buying-signal claims.

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
94% confidence
Finding

The trigger text includes broad phrases like "research this account" and "what do I know about [company]," plus an open-ended condition about preparing for a meeting. In systems that auto-route or invoke skills from natural-language prompts, these vague triggers can cause unintended activation, leading to unnecessary web research, incorrect tool selection, or disclosure of account-research outputs in contexts where the user did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.